SSPAI

Category: App Dev

  • SSPAI Review | Best New Apps to Try This Week

    SSPAI Review | Best New Apps to Try This Week

    DockSide: Put the Empty Space Around Your Dock to Good Use

    • Platform: macOS
    • Keywords: Dock, File Transfer

    DockSide is a lightweight productivity utility designed specifically for macOS. It creates a persistent yet unobtrusive “Shelf” beside the Dock, allowing you to drag and drop files, images, links, text, applications, and folders for quick transfer and organization between different apps.

    The core purpose of DockSide is file staging and transfer, but unlike tools such as Yoink and Dropover, which mainly function as temporary drop zones, DockSide introduces a “temporary shelf” positioned directly alongside the native macOS Dock. The Dock is already one of the most important areas in a typical macOS workflow, and the space on either side of it often goes unused. By making use of these areas, DockSide eliminates the need for additional windows and avoids interrupting your workflow the way floating panels often do.

    The shelf on the left side can be used to store files, linked folders, temporary notes, and more. Files can be quickly accessed through simple drag-and-drop actions. Temporary notes can be created directly within the shelf by typing, pasting, or adding new entries, remaining available there until needed.

    For temporarily stored files, DockSide automatically creates a hidden folder inside the Downloads directory and generates copies to prevent accidental deletion. The app also offers a wide range of advanced settings, including support for up to eight shelf sections for organizing different types of content, automatic deletion of notes and files after 30 days, gesture controls for collapsing and expanding the shelf, and navigation between pages.

    DockSide can also function as a secondary Dock. Since it supports application icons, you can effectively create another Dock alongside the native macOS Dock.

    The shelf on the right side provides additional macOS system capabilities and information. By default, it automatically monitors the contents of the Desktop and Downloads folders, but you can customize it to display the contents of any two locations through the app’s settings. The display area can also be divided proportionally between the selected folders. Beyond file browsing, the right shelf can be configured for media controls and system information. The media view displays and controls currently playing music, with support for Apple Music, Spotify, and more. The information view can display up to eight device metrics, including CPU usage, storage capacity, network activity, and disk usage.

    DockSide supports search, keyboard shortcuts, and gesture-based controls. In terms of appearance, you can switch between light and dark modes, enable Liquid Glass effects, customize shelf height, adjust transparency, and more. You can download the app from the DockSide website. It includes a 14-day free trial, after which a license can be purchased for $5.99, covering up to three devices.

    Permute 4.0: Simplifying Your Multimedia Workflow

    • Platform: macOS
    • Keywords: Multimedia, Format Conversion

    Compared with processing multimedia files through complicated FFmpeg parameters, Permute has long been my preferred solution on the Mac. It avoids unnecessary complexity and lets you achieve the desired media format through simple drag-and-drop actions and clearly described output presets.

    This practical and easy-to-use multimedia tool has continued to evolve. In late May, Permute received its major 4.0 update. In addition to adopting the new Liquid Glass design language of macOS 26, it also introduces a number of convenient new features.

    When you launch Permute 4.0, the first thing you’ll notice is its redesigned user interface. Compared with Permute 3.x, the main window still focuses on its core purpose with a large file-drop area, but the finer UI elements have been fully refreshed to embrace the Liquid Glass aesthetic. After dragging a video file into the window, you’ll see the pre-conversion interface. Opening the output format dropdown reveals two new quick presets: High Quality and Small File, allowing you to choose based on your needs. At the same time, additional source-file handling options have been added, including deleting files directly, moving them to the Trash, or relocating them to a custom folder after conversion.

    For video processing, Permute 4.0 introduces an Auto Settings option for MP4 and HEVC presets. This can intelligently configure parameters such as file size optimization or maximum quality. Hardware acceleration is now also supported for ProRes presets.

    In terms of format conversion, Permute 4.0 improves its cropping tools. When importing videos or images, the crop interface now includes a pixel ruler. If you import audio files, a waveform view is displayed instead. You can also split files using CUE, EDL, or JSON files, and even create custom chapter-based splits. Additionally, subtitles and audio tracks can be dragged directly onto videos within Permute, allowing you to reorder tracks, assign titles, and edit metadata attributes.

    Another interesting feature in Permute 4.0 is the ability to combine images and music into a video. Simply add an image or audio file to the conversion queue, then choose the option to merge the two files and export them as a video. This capability can also be applied to an entire group, enabling batch creation of video outputs from all audio files within that group.

    Other updates in Permute 4.0 include color replacement tools, a completely redesigned metadata editor, automatic repair of webcam recordings, and more. Overall, this is a substantial upgrade built upon the foundation of Permute 3.x. Even if you’ve already used Permute 3.x before, the new features introduced in version 4.0 are well worth exploring.

    You can download and purchase Permute from its official website for $14.99, or access it through Setapp. Existing Permute 3 users can upgrade to version 4.0 for free, provided they have upgraded their system to macOS 26.x.

    Controller for HomeKit: If Siri Can’t Do It, Maybe I Can

    • Platform: iOS
    • Keywords: Smart Home, AI, Siri

    We can use Siri to control smart home accessories in HomeKit, but only for relatively simple tasks, such as “turn on/off a specific accessory in a specific room” or “set the temperature of a specific accessory in a specific room to a certain number of degrees.” That’s pretty much where Siri reaches its limits—anything more complicated and it starts to struggle.

    As for automation, while HomeKit’s underlying framework supports fairly sophisticated configurations, the Home app simplifies much of that functionality and doesn’t expose the full range of capabilities. Apple is expected to unveil a new version of Apple Intelligence built in partnership with Gemini at this month’s WWDC, but some developers in the iOS ecosystem have clearly decided not to wait around. The app featured today, Controller for HomeKit, aims to bypass Siri altogether and build its own AI-powered smart home experience.

    When you open Controller for HomeKit, you’ll notice a plus button in the upper-right corner of the main interface. Tap it, and you’ll find a Create with AI option in the creation menu. This feature is divided into three categories: Add Scene, Add Automation, and Add Workflow.

    Using AI to create a scene as an example, you can simply type a request into the input field or dictate it using voice recognition. Both Chinese and English are supported. Controller for HomeKit uses AI to interpret your intent and automatically generate the corresponding scene. Once the scene has been created, you can open its details, review the configuration, and tap the Save button in the upper-right corner to confirm it.

    Creating automations and workflows with AI follows almost exactly the same process as creating scenes, so there’s little need to repeat the steps. The only thing worth noting is that workflows require Controller Hub to be enabled, which in turn requires a Controller Plus subscription.

    After spending some time with it, it’s fair to say that Controller for HomeKit’s AI-powered creation features do an impressive job of understanding user intent and generating the appropriate scenes, automations, or workflows. If you have demanding HomeKit automation needs, Controller for HomeKit is definitely worth considering.

    Controller for HomeKit is available as a free download from the App Store. The Essentials subscription costs $4.99 per month or $39.99 per year, while the more advanced Plus subscription is priced at $8.99 per month or $79.99 per year.

    Universal Installer: An Elegant, All-in-One App Installer

    • Platform: Android
    • Keywords: Sideloading, App Installation, Shizuku

    The experience of sideloading apps on Android has become increasingly frustrating in recent years. Beyond the countless restrictions and confirmation dialogs added by heavily customized Android skins, Google itself has tightened app installation permissions. On top of that, there’s an ever-growing collection of package formats—APK, APKS, XAPK, and various website-specific formats from sources like ApkMirror. Finding a single tool that can handle every sideloading scenario has become surprisingly difficult.

    Fortunately, there are still plenty of tools that leverage Shizuku to take over Android’s system installer. Universal Installer is one of the most impressive examples I’ve discovered recently.

    Although I’ve tried quite a few similar tools, Universal Installer raises the bar through both thoughtful design and powerful functionality. It adopts Material 3 design principles and supports dynamic color theming. Combined with exceptionally smooth transition animations throughout the installation process, it transforms a utility that would normally be “invisible” into something genuinely elegant. Functionality-wise, it doesn’t cut corners either. In addition to supporting formats such as APKS, it can automatically handle split packages and OBB data for large apps and games, eliminating the hassle of manually extracting files.

    The most important part of any installer happens after you tap an APK file. In this regard, I believe Universal Installer strikes an excellent balance between practicality and usability. It presents an impressively detailed package information screen—including permissions, version details, and more—and provides advanced options that allow for deeper customization, giving users much more control over the installation process.

    Beyond manually installing files, Universal Installer also offers multiple ways to manage and transfer packages. It can directly scan your device storage for installation files, functioning much like a file manager. A built-in lightweight download tool allows you to paste official download links for large games, automatically downloading and installing them afterward. It also supports local network transfers: simply enable the service from the top-right corner of the main screen, and any device on the same network can upload apps directly.

    It’s fair to say that Universal Installer opens up virtually every possible channel for acquiring and installing app packages.

    Universal Installer doesn’t stop at handling new installations—it also takes care of the apps already on your device. It includes a comprehensive application management toolkit with features such as search and sorting, app information viewing, APK extraction and sharing, and batch uninstallation. When paired with Shizuku, Universal Installer unlocks even more advanced capabilities. For example, its “Installer Source Spoofing” feature can disguise installations as originating from Google Play, helping bypass certain annoying restrictions and warnings—or simply satisfying users with a bit of digital OCD, since “Installed from Unknown Sources” isn’t exactly pleasant to look at. It can also automatically approve permission requests for trusted apps, saving you from manually granting them the first time an app launches.

    On the security side, Universal Installer supports biometric authentication for both installation and uninstallation actions. It also integrates with VirusTotal through an API interface. Once you configure your API key, the app can compare package file hashes against VirusTotal before installation, helping you avoid potentially dangerous software.

    If you’re still putting up with Android’s default installer, I highly recommend setting up Shizuku and replacing it with Universal Installer. And even if you’re already using a third-party installer, this one is worth trying—you may find it surprisingly impressive. Universal Installer is available as a free download from Google Play, GitHub, F-Droid, and IzzyOnDroid.

    AirPlay Server: Turn Your Android Phone into an AirPlay Receiver

    • Platform: Android
    • Keywords: AirPlay, Android, Multi-Device Users

    Apple’s ecosystem has long been praised for the seamless connectivity and collaboration it provides across devices. In recent years, many Chinese Android manufacturers have taken a different approach, trying to integrate their own devices into the Apple ecosystem as much as possible. AirPlay Server follows a similar idea, allowing Android devices to function as AirPlay receivers capable of receiving both video and audio streams from Apple devices.

    Using AirPlay Server is remarkably straightforward. After installing the app, simply tap the Start button on the home screen, and your Android device will become discoverable as an AirPlay receiver. On your Apple device, open Screen Mirroring, search for the corresponding device name, and you can begin mirroring content from your Apple device to Android in real time.

    Using my iPhone as an example, following these steps allows the phone’s display to be mirrored directly to an Android device. Once connected, every action performed on the iPhone appears almost instantly on the Android screen. Latency is impressively low, and when audio is playing, the sound is also output through the Android device.

    If your setup happens to be an Android tablet paired with an iPhone, this provides a simple solution for viewing iPhone content on a larger screen.

    On the Android side, mirrored content is displayed in full-screen mode by default. Pressing the Back button returns you to the app’s main interface, where the mirrored content continues to be shown. If you need to use the Android device while simultaneously monitoring content from the Apple device, you can minimize the stream and display it in a floating window overlay.

    Beyond the basics, AirPlay Server also offers customization options for users with specific requirements regarding image quality and frame rate. The app includes a range of common resolution and frame-rate settings, along with built-in decoders optimized for different media formats.

    Audio streaming is equally well supported. Music currently playing on an Apple device can be transmitted to the Android device via AirPlay, with album artwork, playback progress, and track information displayed correctly on the Android side. The app also allows you to control playback and switch tracks directly from the Android device.

    If AirPlay Server sounds interesting to you, you can download it from F-Droid and give it a try. The app is open source and completely free to use.

    Touch Time: A World Clock with Grace and Charm

    • Platform: iOS
    • Keywords: World Clock, Design, Beautiful UI

    World clocks are hardly a new feature, nor are they something most people think about every day. They come preinstalled on almost every mobile device. But if you regularly use a world clock and find the one built into iOS a little too plain, Touch Time might offer a more elegant experience. Rather than simply telling you what time it is, it blends time with local light conditions and weather, allowing you to immerse yourself in the atmosphere of each location and feel closer to the passage of time itself.

    Touch Time’s biggest highlight is its UI design. Drawing inspiration from the Liquid Glass aesthetic, it combines dynamic backgrounds that reflect real-time sky colors and weather conditions in different locations. Whether it’s the endless daylight of Oslo’s midnight sun or a rainy afternoon in New York, you can instantly sense the mood of a place from the time list alone. For users who frequently communicate with overseas colleagues, clients, friends, or family members, this approach feels far more intuitive than simply checking time differences. You can also enrich each time card with features such as an analog clock, sun elevation indicator, temperature display, and more. If you find the visual richness distracting, however, you can open the menu in the upper-left corner and disable weather and sky color displays, returning the app to a more minimalist appearance.

    Touch Time also adds a timeline slider along the bottom of the app. By dragging the slider left and right—or rotating the dial in the “Clock Face” section—you can easily visualize how different time zones correspond to your local time. If you’re planning an international meeting at 2:00 PM, there’s a good chance you’ll be interrupting your colleague’s sleep in New York, so perhaps remember to budget for some overtime pay.

    To improve cross-time-zone coordination, the app includes multi-time-zone alarm and scheduling features. You can create alarms or events directly from any clock card, and the app will automatically calculate time differences and synchronize reminders to your local time. Based on the presets configured under Settings → Calendar, it can also attach city-specific time notes to newly created events, making it easier to share schedules with others. Paid users can additionally define their own availability windows, helping them quickly determine whether participants in different cities are within reasonable working hours when arranging meetings or activities, reducing the need for endless back-and-forth scheduling discussions.

    Beyond productivity features, Touch Time also delivers a surprising amount of emotional appeal. You can switch to the globe view from the upper-right corner of the home screen and watch time slowly move across the Earth as sunlight and shadow drift around the planet. Alternatively, in the Clock Face section, you can open the built-in filter camera and share your local scenery with friends elsewhere in the world, complete with global time stamps. Touch Time offers an in-app purchase that permanently unlocks advanced displays, availability windows, and other premium features for RMB 148. Since the purchase does not affect the core world-clock experience, it’s probably best to spend some time with the app first before deciding whether to upgrade.

    You can download Touch Time for free from the App Store.

  • SSPAI Review | Best New Apps to Try This Week

    SSPAI Review | Best New Apps to Try This Week

    Halide: Mark III Officially Launches

    • Platform: iOS, iPadOS
    • Keywords: Camera, Film-Style Photography

    @ElijahLee: After 18 months of development and refinement, the renowned mobile photography app Halide has officially launched Mark III. We introduced the preview version of Mark III earlier this year, and now the final release is finally here.

    The core of Mark III is its film-style system, known as Looks. Unlike traditional filters, Halide’s Looks dynamically adjust the image rendering pipeline based on shooting parameters, including color tone, contrast, highlights and shadows, film grain, film-like highlight bloom, HDR rendering behavior, and more. Lux specifically highlighted its collaboration with Hollywood colorist Cullen Kelly in developing the Looks for Mark III.

    Currently, Halide Mark III includes five primary Looks:

    • Valencia: Designed for landscapes and urban photography, featuring strong contrast, high saturation, and clear color separation.
    • Rembrandt: Designed for portraits, emphasizing facial structure with pronounced midtone contrast and natural, consistent skin tones.
    • Nova: Ideal for vibrant landscapes, night scenes, and urban neon environments. Colors are highly saturated, highlights lean toward peach tones, and the overall look delivers a strong cinematic feel.
    • Zephyr: Suitable for a wide range of scenarios, offering gentle film-style contrast and natural skin rendering.
    • Chroma Noir: A black-and-white style characterized by moderate contrast and noticeable film grain.

    The second major highlight of Mark III is that every Look supports HDR rendering. While preserving a film-inspired aesthetic, HDR allows significantly more highlight detail and richer shadow gradation. Lux also revealed that each Look actually has both SDR and HDR versions, meaning every style is powered by two separate rendering pipelines. Users can freely choose between them and enable or disable HDR within the settings.

    The newly added Photo Lab introduces manual photo editing capabilities. Rather than being a full-featured image editor, it focuses on providing a fast and streamlined editing experience. Users can quickly switch between different Looks, toggle HDR and film simulations, adjust exposure, and use real-time previews to find the most suitable result. For those who need more control, a swipe through the tabs at the top reveals advanced editing options, including various photographic parameters, white balance adjustments, cropping, and horizon correction. Photo Lab also supports iPad, allowing users to edit photos on a larger screen.

    As we mentioned in our earlier coverage, Mark III completely redesigns the app’s interface. After downloading the latest version of Halide from the App Store, users can tap the new ③ button on the screen to switch to Mark III. The default interface is now cleaner and more streamlined, keeping core functions such as focus, focal length selection, and RAW capture readily accessible, while moving most other controls into the “…” menu on the right.

    Overall, Halide Mark III pushes innovation in digital film-style photography even further. By leveraging modern imaging technology, it significantly enhances the film photography experience while remaining easy to use. With just a few adjustments, users can create images that feel far more like finished photographic works. Halide can be downloaded for free from the App Store, but a paid subscription is required to access Mark III. Pricing is ¥68 per month, ¥148 per year, or a one-time purchase of ¥398.

    Raycast for Mac v2: A New Era for Productivity Launchers

    • Platform: macOS
    • Keywords: Launcher, AI

    @Vanilla: As one of the most successful newcomers in the Mac launcher space, Raycast has firmly secured its place among the top-tier productivity tools. With the recently released Version 2.0 update, Raycast has undergone another major round of improvements and refinements, pushing launcher applications into an era where they feel both all-in-one and indispensable. In the following sections, I’ll highlight some of the most important additions and changes in this release to help you better understand the new Raycast experience. If you’re unfamiliar with launcher tools or Raycast itself, you may want to start with our previous introduction article.

    First, Raycast 2.0 introduces an entirely new design language, primarily created to align with the Liquid Glass aesthetic of macOS Tahoe. The interface is now more compact and streamlined, allowing more items to fit within the same window size. At the same time, Raycast has improved data interoperability across its ecosystem. For example, information retrieved through AI Chat can now be saved directly into Raycast Notes without leaving the workflow.

    Second, Raycast’s file search functionality has become a genuine replacement for the system Spotlight search. In the new version, Raycast has upgraded its indexing engine, making file searches noticeably faster. More importantly, file searches can now be initiated directly from the main search interface, eliminating the need to first invoke a dedicated file-search command before entering keywords. This significantly improves workflow efficiency.

    The Quicklink feature has also received a comprehensive overhaul. First, Quicklinks can now be pinned, allowing users to access them directly without searching by keyword. Second, multiple tags can be assigned when creating a Quicklink, making it easier to organize and filter results. Third, a new “Prefer Existing Tabs” option has been added to the settings; when enabled, Raycast will reuse tabs that are already open in the browser instead of creating duplicates. Fourth, when Finder or a browser window is active, creating a Quicklink automatically populates the current local file path or URL.

    AI has also become a central pillar of the Raycast experience. In Version 2.0, Raycast not only redesigned the AI Chat interface, but also introduced features commonly found in modern coding assistants, including Agents, Memory, and Skills.

    Finally, Raycast has launched a new speech transcription feature. It automatically detects the spoken language, transcribes the content without requiring manual language selection, and can automatically paste the result into the currently active application window.

    Raycast v2 is currently available in beta. You can visit the official website to learn more about the update and download the client. I would recommend every Mac user give Raycast a try. It brings together nearly every productivity tool commonly used on macOS, works out of the box, and requires no knowledge of scripting or automation commands to get started.

    Mactracker 5.0: Build Your Own Apple Product Collection Database

    • Platform: iOS / iPadOS / macOS
    • Keywords: Apple Product Database

    @化学心情下2: As one of the world’s most influential consumer electronics companies, Apple’s extensive lineup of products released since its founding effectively tells the story of the evolution of modern consumer technology. Because of this, developers have compiled detailed information on Apple’s products over the years, making it easier for digital archaeology enthusiasts like us to explore some of the company’s most fascinating historical devices. Mactracker is one of the most well-known Apple product databases available today, offering comprehensive information through its Mac, iPad, and iOS apps. Recently, its mobile version received the major v5.0 update, introducing several noteworthy new features.

    The most eye-catching addition is the new comparison feature, which works similarly to Apple’s own product comparison tool—much like when you’re considering a new iPhone in the Apple Store and want to compare it with the previous generation. In Mactracker 5.0, after locating a product, you can tap the “Compare” button in the upper-right corner to add it to a comparison list. Then, from the comparison page, tap the search button in the upper-right corner to add another product and compare both devices side by side on the same screen. Tapping the marker icon near the top of the screen highlights specifications that differ between the two products, making it easy to spot the key differences at a glance.

    Another new feature is “My Models,” which is designed to catalog the Apple devices you currently own and use. Switch to the My Models section, tap the add button in the upper-right corner, and select “Change Model” to search the product database for your specific device, or allow the app to automatically retrieve information from the current device. You can also record details such as serial numbers and exact model identifiers, gradually building a personalized Apple product collection of your own.

    As a feature that debuted in v5.0, My Models still feels somewhat basic at this stage. Beyond displaying your collection, the “Summary” view in the upper-right corner provides statistics on device categories, color variations, and release-year distribution. Thanks to iCloud Drive integration, this information can also be synchronized across Mactracker installations on your other Apple devices.

    In addition, Mactracker 5.0 expands and refines parts of its database, including new MagSafe battery information for the iPhone Air and detailed entries covering the latest Apple operating systems.

    If you’d like to carefully organize your own Apple hardware collection—or if you’re simply interested in Apple’s product history—it’s well worth giving Mactracker a try. The app is available as a free download from the App Store.

    Caffeine Health: Maybe It’s Time to Cut Back on Coffee

    • Platform: Android
    • Keywords: Coffee Logging, Caffeine Tracking

    @Peggy_: As the coffee market continues to expand, coffee drinks—once a relatively niche interest—have become increasingly mainstream. Coffee is now marketed much like milk tea, and many consumers casually drink two cups a day without much thought. At the same time, caffeine levels in milk tea products continue to rise, while energy drinks are being promoted more aggressively than ever. We have likely never consumed as much caffeine as we do today.

    Caffeine has long been celebrated for its stimulating effects, but every coin has two sides. Excessive caffeine intake can disrupt sleep quality and negatively affect digestive health. Caffeine Health is an app designed to track caffeine consumption. By recording both the amount of caffeine consumed and the timing of intake, the app makes caffeine’s effects on the body visible and presents them clearly through charts and visualizations.

    When first launching Caffeine Health, users are asked to answer a series of questions. Information such as age and body weight is used to estimate a personalized caffeine baseline. Users also provide their typical sleep schedule, allowing the app to recommend an appropriate time to stop consuming caffeine each day. To improve the accuracy of its recommendations, Caffeine Health also asks about habits such as smoking and alcohol consumption. Impressively, the app even cites scientific literature to support how these factors may influence caffeine metabolism.

    Most caffeine-tracking apps focus solely on recording consumption data, but Caffeine Health also takes factors such as liver function and medication use into account—variables that many people tend to overlook in daily life.

    After completing the setup process, Caffeine Health generates personalized recommendations. Based on my own data, for example, the app estimated that caffeine has a half-life of approximately five hours in my body, while the residual caffeine threshold likely to affect my sleep is around 44 milligrams. Of course, these values are only estimates. If you have a better understanding of your own physiology, the app allows you to adjust them later through the settings menu.

    On the app’s home screen, the most prominent element is the chart displayed at the top. As you begin recording caffeine intake, the chart visualizes the timing of each consumption event and provides intuitive recommendations. Tapping “Add” allows you to start logging beverages. Caffeine Health includes a wide range of common coffee drinks for quick entry, as well as many popular energy drinks available on the market.

    If you also enjoy caffeinated beverages such as cola or hot chocolate, Caffeine Health provides estimated caffeine content for those drinks as well. Since the app was not developed specifically for the Chinese market, some beverages and milk tea brands commonly found in China are not included in the database.

    Using today’s coffee intake as an example, I had a homemade pour-over coffee at 9 a.m. and an Americano at 1 p.m. After accurately logging both the quantity and time of consumption, the home screen chart clearly showed how the caffeine from each drink was metabolized over time. It was easy to see that the caffeine from the morning pour-over had largely been processed and was unlikely to affect my sleep. The afternoon Americano, however, pushed my caffeine level significantly higher and would most likely have an impact on my sleep later in the day.

    The greatest strength of this chart is that it quantifies caffeine metabolism in a meaningful way. Advice such as “don’t drink coffee in the afternoon” transforms from a generic warning everyone has heard into a concrete, data-driven visualization that is far more convincing. Additionally, whenever caffeine is consumed during a period that may affect sleep, the app provides appropriate warnings and recommendations. Over time, users naturally develop a better understanding of when they should be more cautious.

    If Caffeine Health sounds interesting to you, you can download it through F-Droid and give it a try. The app is open source and completely free to use, although it does not currently offer a Chinese-language translation.

    PairPods: A Simple Audio Sharing Utility for macOS

    • Platform: macOS
    • Keywords: Audio Sharing

    @Snow: Two people sharing a pair of wired earphones has long been a classic romantic trope in movies and TV shows. But in a world dominated by true wireless earbuds, sharing a single pair no longer brings people physically closer—instead, it often means dealing with mono audio and uneven ear pressure. Fortunately, since Apple introduced Audio Sharing for AirPods in 2021, other manufacturers have gradually followed suit, giving wireless earbuds a much more elegant way to share audio.

    Perhaps Apple has yet to realize the enormous potential of the Mac as a portable streaming machine, because enabling audio sharing on macOS still requires more than simply pairing Bluetooth headphones. Users must open Audio MIDI Setup, create a Multi-Output Device, and manually select the desired audio outputs before sharing can work. For average users, that’s a fairly high barrier. PairPods simplifies and visualizes the entire process. Whether you want to listen to music with a friend on a train or watch a horror movie with someone special in a tiny rented apartment, PairPods makes shared listening easy.

    Audio MIDI Setup Multi-Output Device Configuration Page

    Before using PairPods, I have one piece of bad news and one piece of good news. The bad news is that you still need to follow the instructions and pair all Bluetooth headphones you want to share audio with manually through macOS. The good news is that PairPods is not limited to a specific ecosystem—any Bluetooth audio device compatible with macOS can be managed through the app.

    Once your Bluetooth devices are connected, click the PairPods icon in the menu bar to open its pop-up panel, where all connected audio devices will be displayed. PairPods provides individual volume controls, sharing checkboxes, and sample rate information for each device. Some devices can even display their remaining battery level. Simply enable the “Share Audio” switch at the top of the panel, and the menu bar icon will turn blue while all selected devices immediately begin receiving shared audio.

    When Audio Sharing is enabled, the system volume controls are disabled and PairPods takes over volume management entirely. Turning off the switch immediately stops sharing and routes audio to the device marked with the illuminated crown icon, while restoring the system’s normal volume controls.

    That said, in the current version, switching audio output devices while Audio Sharing is disabled is not entirely seamless. On my MacBook Air, changing the crown-designated device alone had no effect; I had to toggle the Share Audio switch off and on again before the new output device became active.

    To improve stability and usability when multiple Bluetooth devices are connected, the app also includes an automatic reconnection feature. Users can enable automatic reconnects and configure timeout intervals of 5, 10, or 30 seconds. In practice, however, this feature mainly helps reconnect headphones when you briefly move out of Bluetooth range and then return. It cannot solve connection drops caused by highly congested environments such as train stations or shopping malls filled with countless wireless devices.

    PairPods is completely free and open source. You can download and use it from its GitHub project page.

    MedTimer: An Open-Source, Local-First Medication Reminder

    • Platform: Android
    • Keywords: Medication Reminders, Medication Tracking

    @化学心情下2: After being diagnosed with Generalized Anxiety Disorder (GAD), I found myself needing long-term medication and began searching for a tool that could remind me to take my medication accurately and consistently.

    At first, I relied on to-do list apps for reminders. The biggest drawback, however, was their inability to provide detailed medication statistics—such as total doses taken over a week or the exact time each dose was actually taken. Later, I switched to dedicated medication reminder apps like Medisafe. Compared to the bare-minimum functionality of a to-do list app, Medisafe felt almost perfect: it includes a built-in medication database, allows users to search for medications and add daily reminders, offers multiple reminder methods beyond standard notifications, provides detailed usage statistics, and even unlocks professional medication guidance with its Pro subscription.

    For someone like me, however, who has already been undergoing long-term treatment, Medisafe’s premium features and account synchronization weren’t particularly useful. What I really needed was a medication reminder app that worked entirely on-device. Since Android is my primary platform, the open-source MedTimer eventually caught my attention.

    At the time of writing, I’ve been using MedTimer for over a year. The two features that impressed me most are its open-source nature and local-first philosophy. Being open source means there are no bloated commercial features that I’ll never use. Being local-first means I don’t need to synchronize account data—having reminders delivered reliably to my Android phone is all I need, and it perfectly matches my workflow.

    Of course, compared to commercial alternatives, MedTimer still has some limitations. The most obvious one is that medications must be entered manually by name. In Medisafe, entering a brand name is usually enough to retrieve detailed medication information and dosage specifications. That said, manual entry has its advantages as well—you can organize medications however you prefer, and after all, the reminders are meant for your own use.

    The next step is creating recurring reminders. Tapping the “New Reminder” button in the lower-right corner presents several reminder types, each accompanied by Chinese-language explanations. For my own needs, I selected “Scheduled Reminder.” Simply entering the dosage and time in the dialog box is enough to create a reminder. Afterward, tapping “Advanced Settings” unlocks additional options such as reminder status, recurring schedules, weekday-only reminders, reminders on specific dates each month, and more. There’s also an “Enter Actual Dosage” option, which allows users to record the amount actually taken when a reminder appears. This is particularly useful for tracking remaining medication supplies—especially psychiatric medications—and helps remind me when it’s time to schedule a prescription refill.

    Once everything is configured, the MedTimer home screen displays the day’s medication schedule: when reminders were triggered, when doses were actually taken, and which medications still need to be taken today. In addition to the current day, users can also review records from the past week. There is also an “Add One-Time Medication Record” button on the home screen, making it easy to quickly log unscheduled doses.

    The “Record Analysis” section provides a comprehensive view of recent medication history. The summary view shows overall adherence and completion rates, the list view displays individual records with medication names, dosages, reminder times, and actual intake times, while the calendar view organizes medication history by day. The entire treatment process becomes easy to review at a glance.

    Overall, MedTimer is already a remarkably complete open-source, local-first solution. It not only delivers reliable medication reminders, but also records and analyzes medication history in detail, helping users avoid missed doses during long-term treatment. It even supports special scenarios, such as “sleep-in reminders” for weekends and holidays, allowing the first daily reminder to be postponed when sleeping later than usual. If you’re looking for a medication reminder app without excessive commercial features, MedTimer’s open-source and local-first approach makes it an excellent choice. The app is available for free with all features included through both the Play Store and F-Droid.

    GitSync: Making Git Synchronization Easier on Mobile

    • Platform: Android
    • Keywords: Git

    @大大大K: Originally designed for software development, Git has gradually found its way into many everyday workflows, from synchronizing knowledge bases to backing up configuration files. As these use cases become increasingly common, the demand for using Git on mobile devices has grown as well. Unfortunately, working with Git on a phone is rarely straightforward: command-line tools like Termux can be cumbersome, while traditional third-party Git clients often feel too geared toward power users. When I was looking for a Git-based solution to synchronize my Obsidian vault, GitSync turned out to be exactly what I was looking for.

    Unlike many Git tools that overwhelm newcomers with complex terminals and command-line interfaces, GitSync adopts a clean and intuitive graphical interface. That simplicity doesn’t come at the expense of functionality, however. The app includes virtually all of the Git operations most users need on a daily basis. In addition to the standard workflow of cloning, pulling, committing, and pushing, GitSync supports full branch creation and switching capabilities. It even includes a visual interface for resolving Git merge conflicts. What impressed me most was that GitSync comes with its own file manager and a lightweight text editor with syntax highlighting. This allows developers to perform quick code reviews directly on their phones, while regular users can make simple edits to Markdown notes without switching to another app.

    Another standout feature of GitSync is its flexible synchronization system. The app can automatically perform background synchronization whenever a specific app is opened or closed, and it also supports scheduled synchronization tasks. For users who prefer manual control, synchronization can be triggered through quick settings toggles or the app icon’s context menu. Personally, I prefer triggering GitSync whenever I open or close Obsidian, as it helps ensure my knowledge base remains fully synchronized. That setup does require enabling Android’s Accessibility Service, however.

    Configuration is also remarkably user-friendly. GitSync supports OAuth authentication for popular hosting platforms such as GitHub, GitLab, and Gitea. It can also connect to self-hosted Git services through HTTP or SSH keys. In most cases, you simply follow the app’s setup wizard step by step, and everything is configured without much hassle.

    Beyond basic Git functionality, GitSync also supports connecting to large language models through API keys, enabling AI-assisted Git workflows and content completion. This makes lightweight development tasks on mobile devices even more convenient.

    Although GitSync is not a brand-new app, the growing popularity of AI-driven tools such as OpenClaw and Vibe Coding has sparked renewed interest in “AI-ready” knowledge bases, particularly Obsidian, along with the desire to access and manage them on the go. In that context, having a capable Git client that can handle a variety of scenarios becomes increasingly valuable.

    Thanks to its combination of ease of use and comprehensive functionality, GitSync was featured on Obsidian’s annual tools list in 2024. If you have similar needs, this open-source and community-endorsed tool is definitely worth trying. The free version supports connecting a single repository, while the paid version allows multiple repositories to be managed simultaneously. The Google Play version additionally supports Git LFS and filter features. GitSync is available for download from both GitHub and Google Play.

    App Briefs

    • Previous rumors suggested that Apple plans to introduce a standalone Siri app in iOS 27, featuring both text and voice conversations, conversation history, and more. Last week, Mark Gurman stated that he had obtained several screenshots of the app and shared them with readers.

    Source

  • SSPAI Review | Best New Apps to Try This Week

    SSPAI Review | Best New Apps to Try This Week

    VWFNDR™ + MBL: An Android-Exclusive Camera App with Distinctive Interaction Design

    • Platform: Android
    • Keywords: Camera, Third-Party, Manual Controls, Interaction Design

    @克莱德: Nuevo Tokyo Design Studio first became known for its concept camera designs and small creative hardware projects. I personally started following them because of one particularly unique camera concept. Later, they also released a black-and-white film simulation tool called AgBr.

    This new VWFNDR™ + MBL also recreates one of their earlier camera hardware concepts.

    Much like AgBr being exclusive to the Apple ecosystem, Nuevo Tokyo unexpectedly launched a new Android camera app called VWFNDR™ + MBL last week.

    The “VWFNDR” in the app’s name already hints at its core feature. Nuevo Tokyo brought many design ideas from its earlier VWFNDR concept camera series into the app itself. The gallery, viewfinder, and control area are arranged in a continuous vertical (or horizontal, depending on orientation) layout. Swiping up and down seamlessly switches between photo aspect ratios, while pulling the viewfinder down into full-screen mode opens the gallery. Combined with crisp sound effects, well-tuned haptic feedback, and a control area that responsively changes layout based on available space, the entire experience feels smooth and refreshingly original.

    In practical use, the app runs very smoothly on my Pixel 9 Pro, though there’s a slight delay in image processing after taking a photo—you’ll need to wait a moment before previews appear in the gallery. Controls follow the traditional manual-camera approach, offering exposure, shutter speed, focus distance, and more, while also supporting camera-style P and S modes for switching control behavior.

    The only real issue right now is that the current version cannot access lenses other than the main camera. In a follow-up blog post, Nuevo Tokyo harshly criticized the inconsistency of multi-camera APIs across Android hardware. They simply couldn’t achieve a unified, seamless multi-camera switching experience across different devices, so they decided to skip multi-camera support entirely. A pretty stubborn move, honestly.

    Pixel 9 Pro stock camera (left) vs. VWFNDR™ + MBL (right) image comparison

    As for image quality, VWFNDR™ + MBL bypasses the hardware manufacturer’s ISP post-processing pipeline. It captures DNG RAW files directly and then generates JPEGs using its own processing algorithm. You can also enable simultaneous RAW + JPEG saving in settings. The resulting images focus on minimal post-processing and lighter computational photography, delivering a strong optical feel. If you dislike the overly painterly or plasticky look of many stock camera apps, VWFNDR™ + MBL will probably appeal to you.

    You can download VWFNDR™ + MBL from the Play Store, and the app is completely free.

    Pedometer++: Redesigning the Apple Watch Experience

    • Platform: iOS, watchOS
    • Keywords: Step Tracking, Hiking, Walking Exercise

    @ElijahLee: Pedometer++ is a long-running pedometer and walking exercise app that, after years of refinement, has gradually evolved into a complete tool focused on outdoor walking, hiking, and light exercise tracking. Recently, the app released its major 8.0 update, with nearly all changes centered on rebuilding the Apple Watch experience. The developers even describe it as a completely redesigned watchOS app.

    The first thing you notice is the fully dashboard-style homepage. On Apple Watch, the app uses large typography to display daily step counts, with walking distance and floors climbed shown as secondary information. More eye-catching is the progress ring below, which uses roughly one-fifth of a circular ring to indicate progress. The color gradually fills as you approach your goal, visually resembling Apple’s native Activity rings, but focused specifically on walking.

    Scrolling down from the homepage opens the workout selection list, which has also been redesigned in the new version. Apple redesigned the Workout launch interface in watchOS 26, adding many buttons that make operation more cumbersome, while Pedometer++ does the opposite by returning to an earlier approach with large buttons and bigger touch targets, making it easier to use during exercise.

    The newly introduced Expedition Mode is the core feature of this update. In this mode, the app no longer continuously monitors heart rate at high frequency, instead relying on Apple Watch’s lower-power heart-rate sampling to significantly reduce battery usage, extending battery life by up to 40%. The feature makes a lot of sense, since when hiking, people often care more about battery endurance than heart rate tracking.

    Finally, the map experience has been significantly improved, now spread across five pages to present multidimensional information. The main watch face page displays the route map in real time, with support for switching between dark/light map modes and different visual styles. Rotating the Digital Crown switches between additional watch pages, which permanently display distance while also showing pace, steps, floors climbed, elevation changes, heart-rate zones, and more. The interface is also very convenient to operate while exercising.

    You can download Pedometer++ for free on the App Store. A paid subscription unlocks the premium version, which includes workout tracking, training plans, weather information, and Apple Watch map functionality. Pricing is ¥15/month or ¥198/year.

    Tripsy Update: Adding Claude MCP Brings Travel Planning Into the AI Era

    • Platform: iOS / iPadOS / watchOS / macOS / visionOS
    • Keywords: AI, Travel Planning, Claude

    @Vanilla: Honestly, travel planning is exhausting. Even though we already have tools like Tripsy to help collect, organize, and manage itineraries, most of the work still has to be done manually, and the longer the trip, the more complicated adjustments become. Finally, in its latest update, Tripsy introduced its own MCP tool that can be used directly inside Claude or Claude Code. With Claude’s powerful capabilities, we can now plan trips much more efficiently.

    The first step: taking Claude Desktop as an example, switch to the Code interface, click the Customize button in the left sidebar, choose “Connectors,” then click the + button to add a custom connector. You can name it anything you like. In the URL field, enter https://mcp.tripsy.app, then click Add.

    Once added, you’ll see all the tools provided by Tripsy MCP, including 17 read-only tools and 19 editable/deletable tools. Each tool can have individual permissions configured, including Always allow, Needs approval, Block, and Custom.

    The second step: return to the Code interface and start a new conversation. Then simply describe the travel itinerary you want Tripsy to create, with as much detail as possible. After a short wait, Claude will generate an itinerary matching your requirements and write it directly into the Tripsy app through Tripsy MCP.

    The third step: if you notice anything unsatisfactory in Claude’s generated overview or while viewing the itinerary directly inside Tripsy, you can simply ask Claude to modify it. You can provide alternative options for replacement, or let Claude search for recommendations on its own.

    Finally, when you return to the Tripsy app, you’ll see a complete travel itinerary, including flights, accommodations, locations, routes, and detailed information for every stop.

    At this point, I don’t think much more needs to be said—Tripsy MCP feels like the ideal solution for travel planning in the AI Agents era. Tripsy can be downloaded for free from the App Store. A subscription unlocks expense management, reservation forwarding, advanced travel statistics, calendar subscriptions, daily activities, 10-day weather forecasts, timezone changes, and more. Pricing is $7.99 per month or $39.99 per year, with a 7-day free trial available, and it’s also included with Setapp. For me personally, with Tripsy MCP and Claude, the free version is already more than enough.

    GoalKit: Let AI Help You Break Down Your Goals

    • Platform: iOS / iPadOS
    • Keywords: Habit Building, Goal Management

    @Snow: Habit-building apps and to-do list apps are two types of tools we often use when breaking down goals in daily life, and GoalKit attempts to merge both into a single framework. Instead of focusing solely on daily habit check-ins or task completion, it helps users break long-term goals into executable and trackable steps, so you won’t give up halfway because a goal feels too ambitious. By taking small steps every day, eventually you’ll arrive at your destination.

    GoalKit offers four different goal types: one-time checklist goals, quantifiable progress goals, milestone goals suited for long-term planning, and habit goals for cultivating daily behaviors. Whether you’re preparing for a trip, learning a new skill, or organizing a project, GoalKit can basically cover most everyday goal-management needs. For example, if you’re currently preparing for a home renovation, you can use milestone goals to divide the process into stages such as clearing waste, structural adjustments, and furniture purchasing. Combined with daily progress check-ins, milestone goals help provide a clearer understanding of completion status and expected timelines for each stage.

    If you’re unsure which goal type suits you best, you can rely on GoalKit’s built-in AI capabilities. When creating a goal, you can describe your objective in natural language and tap “Create with AI.” The AI will automatically match the appropriate goal type, break down the plan, and add notes for you. During execution, the AI can also provide more detailed recommendations based on your progress.

    The bottom drawer of the app includes two sections: “Goals” and “Insights.” After completing a certain number of tasks, you can track the progress of each goal in the “Insights” section. Scrolling to the bottom of the page reveals an AI summary. If you don’t have time to study detailed data and progress reports, this AI-powered “too long; didn’t read” version may be exactly what you need.

    GoalKit includes a subscription service priced at $3.99 per month or $15.99 per year, with a one-time lifetime purchase option for $29.99. Paid features unlock unlimited goals, widget syncing, image attachments, and more.

    GoalKit is not yet available on the China App Store, but you can download it for free from the U.S. App Store.

    Vivaldi 8.0: Rebuilt Interface with Six New Preset Layouts

    • Platform: macOS / Windows / Linux
    • Keywords: Browser

    @化学心情下2: Desktop browsers today are almost entirely dominated by Chromium, but browsers like Chrome, Edge, Opera, and Vivaldi all differentiate themselves through interface design. The problem is that users can barely customize these interfaces in depth—at most, you can change a theme, while adjustments to title bars, menu bars, and other modules remain extremely limited. For browsers like Chrome and Edge that prioritize out-of-the-box simplicity, this may not be a major issue, but for Vivaldi, which is known for extensive customization, it’s a different story.

    As a result, Vivaldi 8.0 doesn’t introduce a flashy new feature like previous major releases. Instead, it completely reconstructs the browser interface in what the company calls the “Unified UI.” The fragmented feeling caused by stacked components has been eliminated, with all browser elements now treated as different layers of the same system, unified through consistent alignment and spacing while smoothing out subtle design inconsistencies between components. According to Vivaldi, the new interface creates a more cohesive theme throughout the browser, eliminating awkward color mismatches between tabs and backgrounds. Combined with translucency and blur effects, transitions now feel much smoother visually.

    Vivaldi has always been known for its rich layout customization options, but new users often don’t know where to begin. To address this, version 8.0 introduces six preset layouts: Simple, Classic, Auto-Hide, Bottom Tabs, Vertical Left Tabs, and Vertical Right Tabs. New users can quickly pick a layout that matches their habits and later customize it further as needed.

    Beyond the Unified UI, Vivaldi 8.0 also brings a series of optimizations to the panel editor and start page. The browser supports macOS, Windows, and Linux, and can be downloaded for free from the official website.

    Braincup: Stop Mindless Scrolling, Start Training Your Brain

    • Platform: Android
    • Keywords: Brain Training

    @Peggy_: The last time I realized my memory was deteriorating was after staying up all night, when I simply could not remember the pickup code for a Hive parcel locker. The panic I felt over such a tiny incident was very real. Although proper rest later restored my short-term memory, the experience still served as a wake-up call: I need to keep exercising my brain, stop endlessly scrolling on my phone, and build more positive habits, including but not limited to exercise, writing, and creating. Braincup, the app I’m introducing today, is a collection of tools designed to help improve brainpower and reaction speed.

    The next time you unlock your phone and have no idea what to do, maybe use Braincup to make yourself smarter instead. Braincup includes many mini-games designed to train calculation ability, thinking skills, short-term memory, and reaction speed. Familiar categories include Sudoku, mental arithmetic, and Schulte tables. Sudoku and calculation games effectively train math skills, while Schulte tables test concentration. Ghost Grid, Visual Memory, and Orbit Tracking challenge short-term memory. In addition, Braincup also offers Mini Chess and Huarong Dao puzzles to develop thinking ability, while Color Shapes and Color Confusion train reaction speed.

    Opening any mini-game first brings up a brief instruction guide, after which you simply complete the required tasks before the countdown ends. Once time runs out, Braincup calculates a score based on your accuracy and the number of completed tasks. As you play more often, the app also continuously updates your personal high-score records.

    In practice, some of Braincup’s mini-games are genuinely challenging. The most demanding one in terms of concentration and reaction speed is probably Color Confusion, where you must identify the one color word whose text matches its actual color among many misleading options. It feels exactly like being back in a psychology reaction-time experiment. While most games aren’t particularly difficult, Mini Chess allows difficulty selection, giving it more replayability. The next time you’re bored and want to kill time, instead of sinking into short videos, you might as well open Braincup and randomly pick a puzzle game.

    If you’re interested in Braincup, you can download it through F-Droid. The app is completely free.

    App Quick Hits

    • During Google I/O, Google demonstrated the ability to create personal-use Android apps with AI Studio and export them directly to smartphones.
  • SSPAI Review | Best New Apps to Try This Week

    SSPAI Review | Best New Apps to Try This Week

    AIDA: An All-in-One Calendar and Task Planning Tool

    • Platform: iOS, iPadOS
    • Keywords: Scheduling, To-Do Lists

    @ElijahLee: Aida is a calendar and to-do list app developed for iPhone and iPad by Harry, one of the former founders behind the task management app Sorted. It combines to-do lists, calendars, and time planning tools into a single interface for viewing, planning, and taking action.

    The app’s main interface is a daily timeline. At the top is a compact overview of the upcoming seven days, while the center of the screen is dominated by the current day’s time blocks. You can immediately see plans like watching a movie at 10 AM, writing app reviews at noon, working out in the evening, along with reminders to water your plants at night — all without constantly switching between multiple apps. Aida’s quick adjustment feature allows you to simply press and drag events directly on the timeline to reorder your day, while the associated time slots automatically update, making schedule reshuffling extremely convenient.

    Using the add button in the bottom-right corner, you can freely add actions or events to the timeline. Actions function as to-do items, supporting text input and reminder times. Aida creatively introduces a drag-based time-setting system: by swiping the bar chart at the bottom left or right, you can adjust reminder times in 15-minute increments, making time adjustments feel surprisingly intuitive and efficient.

    Of course, you can also tap the time directly for more precise hour-and-minute adjustments. Events in Aida function as standard calendar events and must include both start and end times. Users can also select calendar categories, set all-day events, and more.

    Aida also introduces GTD-style project management features, including default categories such as Inbox, Anytime, and Someday. Custom projects allow users to organize related actions and events together into centralized collections. Aida is deeply integrated with iOS Calendar, allowing users not only to view iOS calendar events directly inside the app, but also to edit and sync them in real time. However, Aida currently does not integrate with Apple Reminders. The batch operations feature allows users to select multiple actions at once to complete, reschedule, move, or duplicate them, making it easy to adjust entire blocks of tasks quickly.

    Aida is available as a free download on the App Store, though the free version comes with significant limitations, including support for only one integrated calendar, no ability to adjust action times, and restrictions on the number of actions and events that can be added. Paid subscriptions unlock advanced features such as unlimited projects, unlimited time blocks, and support for multiple calendar integrations. Pricing is 58 RMB per month, 298 RMB per year, or 698 RMB for a lifetime purchase, with a one-week free trial included.

    Cogito: A Markdown Editor Designed to Connect Humans and AI Agents

    • Platform: macOS
    • Keywords: Markdown, AI

    @Vanilla: By now, I think everyone has seen more Markdown editors than they can count. But with the rise of AI Agents, Markdown as a file format feels like an old tree blooming again, suddenly regaining popularity among a new generation of users. Cogito is a Markdown editor designed for both humans and AI Agents. It is not knowledge-base-oriented like Obsidian, not focused on WYSIWYG editing like Typora, not writing-centric like iA Writer, and not developer-oriented like Visual Studio Code. Instead, its defining characteristic is being “file-first” and “agent-friendly.” So let’s take a closer look at what makes this new-generation Markdown editor different.

    Cogito’s entire library is built directly on the local file system — no proprietary formats, no encryption barriers, no built-in syncing systems. The structure of files and folders mirrors Finder exactly, with zero learning curve. In my own workflow, for example, I directly set Codex’s workspace folder as Cogito’s main location. The app automatically scans all folders and Markdown files inside the Codex workspace, organizes them by date, and presents everything in a clear and intuitive layout.

    After selecting any Markdown file, Cogito opens directly into editing mode by default, allowing us to freely edit content however we like. Clicking the first button in the top-right corner switches between edit mode and preview mode, with the keyboard shortcut Command + R. I often use Codex to generate industry or company research reports in Markdown format, and Cogito makes both editing and reading those files incredibly convenient, eliminating the constant back-and-forth between Codex, Finder, and separate Markdown editors.

    By clicking the second “Outline” button in the top-right corner, users can quickly view the current document’s outline and jump directly to any section by clicking its heading.

    In addition to being AI-Agent-friendly, Cogito can also directly invoke local AI Agents inside the app itself to summarize, analyze, edit, or otherwise process documents displayed within the application.

    Overall, for someone like me who frequently works with AI Agents and Markdown documents, Cogito feels like an excellent Plan B — clearly separated from my primary writing tool iA Writer and my knowledge-base system Obsidian. It launches instantly, gets the job done efficiently, and disappears just as quickly, making it a highly streamlined tool.

    Cogito is currently available as a free download from its official website and is presently in public beta.

    AndDrive: Seamlessly Connect Your Android Device and Mac

    • Platform: macOS
    • Keywords: File Management, Phone Management

    @化学心情下2: While there are already plenty of tools that allow wireless file transfers between Android phones and computers, “transferring files” and “managing files” are two completely different things. For example, if you want to batch-delete screenshots stored inside the Pictures folder on an Android device, traditional transfer tools quickly become awkward to use. This kind of task is far better suited to a desktop file manager, where filtering and preview features make handling large numbers of files much more efficient.

    On Windows, this requires no third-party software at all: simply plug in a cable, select “File Transfer,” and Android is mounted as an MTP device, allowing direct management just like a removable drive. On macOS, however, things become much more troublesome. Since MTP is a Microsoft-specific protocol, macOS can only access Android internal storage either through USB debugging or by relying on third-party MTP implementations. OpenMTP is probably one of the better-known options, but the project has not been updated for more than two years, stability is mediocre, and it relies on its own custom-built file manager instead of Finder, making the overall experience less intuitive.

    So is there a tool that allows Android files to be managed directly through Finder? That’s exactly what AndDrive aims to do. Developed by an independent developer, AndDrive avoids the MTP route entirely and instead builds its file management system on top of Android’s official ADB debugging channel.

    After installation, AndDrive lives in the macOS menu bar and supports both USB and Wi-Fi connection methods. Before using it, users need to enable ADB debugging on their Android device, authorize the current Mac, and install the companion app AndDrive Helper on the phone following the provided instructions. Once completed, the Android file system becomes directly visible inside Finder.

    AndDrive offers several mounting modes, including SD card directory, root directory, or no mounting at all, with each mode exposing different content. The SD card mode only displays internal storage, while the root directory mode additionally exposes the system root directory — though without root access, many files still remain inaccessible. In daily use, users can directly preview files in Finder, filter them by date, or drag files from the Mac directly into Android folders. The experience feels far more intuitive than digging through files using Android’s built-in file manager.

    Because it relies on ADB, AndDrive also includes built-in screen mirroring functionality. Clicking the “Screen Mirroring” option inside AndDrive instantly projects the Android device’s display onto the Mac, offering an experience similar to iPhone Mirroring on macOS. Users can directly interact with apps, perform Chinese-language searches, and even use features such as clipboard synchronization, screen recording, and screenshots. Compared to manually typing scrcpy commands, the barrier to entry is significantly lower.

    Overall, while AndDrive does not use the more mature MTP protocol, it leverages Google’s officially recommended ADB method to make managing Android files directly inside Finder simple and practical, while also adding iPhone-style screen control features. For anyone with this kind of workflow need, it is definitely worth trying.

    You can download AndDrive for free from the App Store.

    Fauxx: A Privacy Tool That Fights Back Instead of Just Defending

    • Platform: Android
    • Keywords: Privacy Protection

    @大大大K: Every search you make, every network request you send, and every bit of your location history is quietly being collected by data platforms and advertisers. They piece together these fragments to reconstruct your identity, preferences, habits, and even the people you interact with most often, before trading your data behind the scenes and feeding you highly targeted ads. That’s why after you or a friend casually search for something, within ten minutes nearly every app and website suddenly starts surrounding you with ads related to that exact topic.

    Because of this, countless privacy protection tools have appeared on the market. Most of them follow the same strategy: “blocking” — blocking data uploads, intercepting cookies, masking IP addresses, and so on. But Fauxx takes a completely different approach. If advertisers insist on collecting data anyway, why not bury the real you inside a mountain of carefully generated “garbage” data?

    The first time you open Fauxx, the app walks you through a setup process where you can optionally enter broad details such as your age range, profession, and interests. The main purpose is to help the app generate misleading profile data that intentionally contradicts your real identity, though you can also skip this step entirely if you want. Fauxx does not force you to provide any personal information. Once setup is complete, you simply enable the main switch to activate its data obfuscation system. The main interface then shows how many “confusion” actions Fauxx has performed recently, which fake persona is currently active, and what types of information are being distorted.

    As for what exactly can be obfuscated, users can configure both intensity and categories through the “Targeting” and “Modules” tabs. The “Targeting” section offers three levels: the first generates noise data intentionally opposite to your real profile, or randomized fake information if you skipped setup entirely; the second attempts to directly interfere with advertiser profiling systems, though in my own testing this feature occasionally failed to load properly — fortunately without affecting overall usability; and the third introduces “persona rotation,” where Fauxx continuously cycles through fabricated identities to make tracking much more difficult.

    Meanwhile, the “Modules” tab contains seven separate obfuscation modules that can each be enabled or disabled individually. Settings also allow users to adjust obfuscation frequency and define active time windows.

    So how do these “fake data” streams actually fool advertisers? Normally, trackers embedded inside apps monitor device identifiers, IP addresses, DNS requests, and other signals to follow browsing behavior across a device and gradually build a user profile. Fauxx fights back by simulating human-like behaviors such as searches and link visits — including pauses while typing and even fake ad clicks — in order to bypass bot detection systems and successfully feed trackers false behavioral data.

    In many ways, Fauxx completely flips the traditional philosophy of privacy protection, shifting from passive defense to active offense. If you want to take a different approach and make life a little harder for advertisers, you can download Fauxx for free from GitHub.

    Roll: Fresh Film Every Day

    • Platform: iOS
    • Keywords: Mobile Photography, Film Simulation

    @Snow: These days, smartphone photography can branch into nearly infinite possibilities. Different lenses, different filters, different manual settings, different image adjustments, even different accessories — as long as you are willing to spend time experimenting, you can master almost any style you want. But more choices often bring more “decision paralysis.” If you are starting to feel overwhelmed by endless options, or simply do not enjoy constantly tinkering with settings in the first place, then Roll might help you rediscover the joy of simple photography.

    Open Roll, complete the brief onboarding process, and you will receive your film stock for the day. The app gives a short description of the film’s characteristics — sensitivity, contrast, saturation, and more. Some film stocks bring warm golden tones beneath sunlight, some shimmer with rose-like hues, and others almost feel as though they are inviting you into a “Close Encounter of the Third Kind.”

    Unlike the random film systems used by most photography apps, Roll gives every user exactly the same “dice roll.” No matter where you are in the world, everyone is shooting with the same film stock at the same moment. The remaining available time for the current film is displayed directly on the film description page. Since time is limited, all that’s left is to press “Load Film” and start shooting.

    Roll does not ask you to switch lenses, tweak colors, or hesitate over endless creative decisions. The only optional feature it provides is a flash toggle for low-light environments. All you need to do is press the shutter button. And honestly, there is something oddly romantic about imagining strangers on the other side of the world creating photos with the exact same film filter at the same time.

    Roll works quite well as a tool for documenting everyday life. But if you are looking for serious or highly professional creative work, its heavily stylized filters and fixed 1080 × 1080 output resolution will probably feel limiting.

    You can download Roll for free from the App Store.

    Sufei: Appreciating the Beauty of Classical Chinese Poetry

    • Platform: Android
    • Keywords: Poetry

    @Peggy_: As a teacher, our workplace still maintains a tradition where every Monday each person writes on a small blackboard. Every week, the person in charge selects a poem fitting the season or occasion, and everyone carefully copies it down by hand. But honestly, after leaving high school behind, how many of us still actively appreciate classical Chinese poetry? Outside of studying or teaching requirements, voluntarily sitting down to read and analyze an ancient poem has become surprisingly rare nowadays. Yet every time I personally copy each line character by character, I still find myself amazed by the elegance and precision of ancient writing.

    Sufei is a practical tool designed to help users appreciate and search classical Chinese poetry. Even from its calm and elegant name alone, it is easy to sense the quiet, refined beauty the developer is trying to convey. Upon opening the app, there are no noisy advertisements or overwhelming visual effects on the launch screen — only a simple message quietly appears: “Preparing rice paper for you.” And somehow, that alone makes you curious about what kind of poem is about to appear.

    One of the app’s core features is presenting a randomly selected poem or ci every hour. In terms of page design, the interface uses a restrained and elegant background while focusing only on the title and one or two highlighted lines from the work itself. The developer chose a clean, readable serif font and arranged the text vertically, creating an atmosphere that feels much closer to traditional Chinese literature. By tapping anywhere on the main screen, users can view the poem’s full content, including annotations for difficult vocabulary, modern translations, and literary analysis. The app also provides historical background information for each work, helping users better appreciate poems they may not already be familiar with.

    Sufei also allows users to search for any poem directly. Beyond basic search functions by title or author, the app includes an extensive tagging system organized by dynasty, literary style, and poetic themes, making it easy to quickly browse specific categories of poetry. For example, poems can be filtered into farewell poems, landscape poems, love poems, and more. Poets’ stylistic schools are also categorized separately, including bold and unrestrained styles versus delicate and restrained styles. Searching by dynasty, ci pattern names, and other literary classifications is equally supported. Tapping any tag immediately displays all related works within that category.

    Of course, users still need to choose tags logically. Selecting combinations such as “Yuan Dynasty,” “Qinyuanchun,” and “Three Hundred Tang Poems” simultaneously will naturally return no results. By swiping left on the tag bar, users can enter the “Tag Plaza,” which also supports direct keyword searches for tags themselves. Searching for commonly used literary themes such as “expressing ideals through objects” or “criticizing the present through historical references” quickly returns relevant poems.

    For works you particularly enjoy, you can tap the heart icon to save them at any time. All bookmarked poems are collected under a section called “By the Pillow.” As an app primarily focused on poetry display and discovery, Sufei’s design philosophy is remarkably restrained. The only customizable options are font size and line spacing, though users dissatisfied with the default color palette can also enable dynamic color extraction. One small drawback is that the sharing function currently supports only plain text exports. If future updates introduced several aesthetically matched share-card templates, it would probably become much easier for users to save and share their favorite lines.

    If Sufei sounds interesting to you, you can download it through F-Droid and try it yourself. The app is completely free.

    App Briefs

    • Obsidian has launched a new Obsidian Community plugin and theme directory alongside a developer Dashboard, introducing improved browsing, submission management, and automated security review mechanisms.
    • OpenAI announced that Codex has been integrated into the mobile version of ChatGPT in preview form. Users can now view progress, guide tasks, approve commands, and continue connecting Codex workflows across local or remote environments directly from their phones.
  • SSPAI Review | Best New Apps to Try This Week

    SSPAI Review | Best New Apps to Try This Week

    Snapseed 4.0: Simultaneous Cross-Platform Update Adds New Lighting Effects Tools

    • Platforms: iOS / Android
    • Keywords: Mobile Photography, Photo Editing

    @Snow: Ever since Snapseed entered the 3.0 era, it has completely abandoned its old “lying flat” attitude and started updating with the intensity of that one ultra-competitive overachiever at your school or workplace. Previously, though, it was only really “grinding” on iOS. This time, it finally remembered it belongs to Google’s family too, bringing the previously updated UI redesign, smart masking, vintage filters, film grain, dehaze, beauty retouching, and many other features to Android alongside the new 4.0 release. If you’d like to learn more about the new features introduced throughout the 3.x cycle, you can check out previous App Picks entries through the related tags.

    Version 4.0 also introduces another round of UI adjustments. It adds some playful eye and finger elements to the startup animation, gives the overall button design a cleaner, more outlined look, and introduces a light background theme that can automatically switch based on system settings. Personally, I find this slightly at odds with iOS’s occasional Liquid Glass aesthetic, and I actually think the 3.x versions felt more visually cohesive. But perhaps this redesign was made for better consistency with the Android version.

    The new version moves the export button from the upper-right corner into the bottom toolbar. Tools and Favorites have now been merged together, and the previous limit of only four favorite tools has been removed. The editing interface also feels more centralized during image adjustments, which definitely deserves praise.

    Version 4.0 also introduces two new style tools: Bloom and Halation. If those names sound familiar, that’s because they’re the same effects introduced in Darkroom 7.0 late last year — now with Google-approved “official” Chinese translations. Bloom softly spreads light throughout an image, creating a dreamy and hazy atmosphere. Halation, meanwhile, simulates the reddish glow old film stocks produced under strong lighting conditions, adding a warm nostalgic feeling to photos.

    Compared with Darkroom, Snapseed’s default effects at the same intensity feel noticeably more aggressive. The Bloom effect spreads farther and appears brighter, while the red glow from Halation is also much more pronounced. Fortunately, Snapseed offers a far richer set of adjustment controls. In addition to intensity, Bloom allows you to tweak size, source range, and softness. Halation is even more professional, offering eight adjustment parameters including intensity, size, hardness, source range, target range, global offset, hue, and grain. This allows for far more diverse halation effects than what Darkroom currently offers.

    Snapseed 4.0 still retains what may be its greatest advantage: it remains completely free and ad-free. You can download it for free from the App Store or Google Play.

    Bevel: Expands AI Features With Support for Personal Health Records

    • Platforms: iOS / watchOS
    • Keywords: Health Data, Health Assistant

    @ElijahLee: The all-in-one health app Bevel has released its 3.0 update, with this version heavily focused on strengthening the new AI health assistant Bevel Intelligence, adding support for importing health records, and introducing practical features such as biological age metrics and personalized recommendations.

    First up is the AI health assistant Bevel Intelligence, a conversational AI agent designed for AI-assisted health analysis. In the upgraded V2 version, users can now choose Bevel Intelligence’s communication and coaching style from four personalities: Data Nerd, Guardian, Friend, and Commander. Each personality specializes in different functions. For example, Data Nerd is more analysis- and detail-oriented, focusing on trends, patterns, and the reasoning behind the data. Friend, meanwhile, takes a warmer and more encouraging approach, placing greater emphasis on companionship and sustained motivation. These personalities extend across AI conversations, notification messages, health recommendations, and more. Of course, as an intelligent agent, it can also adapt to other preferred tones and styles upon request.

    Beyond question-and-answer interactions, Bevel Intelligence now supports morning briefings, reminders, and progress tracking. Users can ask the AI to push scheduled updates on sleep and recovery every day, set reminders for logging food and nutrition information, or generate weekly and monthly summaries and analyses. All of these tasks can now be assisted by Bevel Intelligence.

    Bevel has also introduced a brand-new Biological Age feature, which comprehensively analyzes body, physiological, and blood biomarker data integrated into the app to estimate the body’s current age-related condition. Specifically, the system evaluates five categories of data: sleep, activity, fitness training, lifestyle, and blood biomarkers. The more data you track, the more accurate the results become. Every Monday, users receive an updated biological age report, and can further explore weekly changes and understand which indicators contributed to fluctuations in their age profile.

    Within Bevel Intelligence, the new Files feature replaces the previous Memory function, turning it into a dynamic and persistent information hub used to store workout data, nutrition logs, AI-generated historical content, records, and various other types of information. In essence, it becomes a personal AI-powered data archive that continuously updates over time. The more you use Bevel Intelligence, the more comprehensive and accurate its analysis becomes.

    The arrival of the Files feature also lays the foundation for comprehensive health record management. Inside Bevel, users can upload hospital examination reports, medical checkup records, clinical documents, prescription information, and other healthcare materials, bringing together fragmented health data scattered across different places. Combined with daily physiological data such as sleep, exercise, and nutrition, Bevel Intelligence can then organize and analyze everything together. As a result, Bevel is evolving beyond being just an Apple Watch data collection tool and moving closer toward becoming a one-stop personal health record management system.

    Bevel can be downloaded and used for free from the App Store. AI features require a subscription to unlock advanced functions including check-ins, trend analysis, workout template creation, food logging, and personalized training plans. Subscription pricing is RMB 98 per month or RMB 698 per year, with a three-day free trial available.

    Minis: An AI Agents Platform for Mobile Devices

    • Platforms: iOS / iPadOS / Android
    • Keywords: AI, Local Assistant

    @Vanilla: There’s no need to explain how hot AI Agents are right now, but most of them still primarily run in desktop environments. Xiaomi has already introduced MiClaw on its smartphones, and before that there was the Doubao phone, but truly general-purpose AI Agents like Openclaw, Hermes Agent, Claude Code, or Codex remain relatively rare on mobile devices. Minis, as an independently developed project, has launched dedicated mobile clients for both iOS and Android, while also supporting integration with various LLM services, seemingly aiming to create a mobile AI Agents platform. But is it really? Let’s take a closer look.

    The first time you open Minis, the app prompts you to add an AI provider. Here, I’ll use Gemini as an example. Enter your API Key, leave the custom API address blank unless you’re using a third-party relay service, then tap “Add AI Provider.” Next, choose a model — in my case, I selected Gemini 3.1 Pro Preview — and after that, you’ll enter the chat interface.

    Like other AI Agents, you simply enter instructions into the chat box and let Minis complete tasks for you. But on a closed system like iOS, how does Minis actually make AI Agents work? The answer is that Minis includes a built-in Linux Shell environment. All natural language input from the chat interface is converted by the AI Agent into terminal commands and executed inside the Shell environment. Of course, you can also skip the AI Agent entirely and directly operate through command-line input inside the Shell window yourself.

    Naturally, iOS system restrictions also define Minis’ current ceiling. Even through Shell commands, it can only interact with Apple-approved interfaces such as HealthKit, Calendar, Reminders, HomeKit, Contacts, Bluetooth, Location, Photos, and Speech APIs. In essence, this is not fundamentally different from what Apple Shortcuts can already do. At the same time, Minis also supports creating and invoking Skills, allowing the AI Agent to handle different stages of a workflow for you automatically.

    At this point, I have to say that I don’t think third-party AI Agent tools really have a future on iOS. This is something only Apple itself can properly build. Different AI services can certainly be integrated, but the entry point will almost certainly remain Siri — Apple is unlikely to open that level of system access to third-party apps. Android, meanwhile, may have a slightly brighter future here since its permission controls are far less restrictive than iOS. Whether through third-party apps or customized Android systems, it’s much easier to build something genuinely capable. So if you want to try Minis, I’d actually recommend downloading the Android version instead.

    Minis can be downloaded for free from the App Store or the official website.

    Klack 2.0: Mechanical Keyboard Sound Effects Tailored for Mac

    • Platform: macOS
    • Keywords: Keyboard Sound Effects

    @化学心情下2: We’ve covered quite a few mechanical keyboard simulation apps for macOS in previous editions of App Picks. While the built-in keyboard on a MacBook can’t really reproduce the tactile feel of a mechanical keyboard, hearing satisfying switch sounds while typing still provides a certain kind of joy. But after trying many of these apps, I noticed they all tend to share the same pain point: a lack of contextual controls. For example, adding simulated keyboard sounds on top of an actual external mechanical keyboard feels redundant, and during online meetings, you definitely don’t want everyone else hearing loud typing noises through your microphone. After trying a whole range of options, I ultimately settled on Klack, because the new sleep settings introduced in version 2.0 solve exactly these problems.

    On the sound side, Klack offers a variety of switch types including Black, Brown, Cream, and Purple switches, while version 2.0 also adds the classic Red switch, meaning most mainstream switch sounds are now covered. After clicking the menu bar icon, simply hovering over any option lets you preview the corresponding typing sound in real time. Unlike many similar apps, Klack 2.0 also introduces support for spatial audio. When paired with AirPods, the typing sounds gain a much stronger sense of depth, creating a surprisingly convincing illusion of using a real mechanical keyboard.

    Version 2.0 also introduces a new feature called Tone Pad, located within the sound settings. By dragging the central control point, you can adjust the perceived position and distance of the sound source, making the simulated typing audio feel closer to a realistic environment.

    The Sleep Triggers feature is what I care about most in this update. Under “Settings” > “Sleep Options,” the Sleep Triggers section lists multiple conditions, including connecting an external keyboard, playing music, microphone usage, wearing headphones, being in a meeting, and more. Once any selected condition is met, the app automatically mutes itself. For example, after enabling the external keyboard trigger, Klack automatically stops playing simulated sounds whenever my Mac is connected to an external mechanical keyboard. If you don’t want complete silence and simply prefer quieter sounds, you can enable “Lower volume instead of muting” and separately configure the reduced volume level during sleep mode.

    Overall, Klack 2.0 not only satisfies the desire to hear mechanical keyboard sounds on a Mac, but also eliminates the hassle of manually switching settings thanks to its Sleep Triggers system, making the experience feel much more seamless and unobtrusive. Klack is available on the Mac App Store for RMB 38 as a one-time purchase with no in-app purchases, and it’s definitely worth trying if you’re interested.

    Momentum: Turn Daily Photos Into a “Video Diary”

    • Platform: Android
    • Keywords: Journaling

    @大大大K: Before high school, I used to keep a diary consistently. But as life became busier with age, I gradually stopped sitting down to record my life through writing. That doesn’t mean we’ve lost the ability to document our lives — it’s just that photography has become a faster and more convenient alternative. Posting on social media or shooting short videos has, in many ways, become another form of “diary.”

    If you want something with a bit more ritual and intention behind it, you might want to try an app called Momentum. It can automatically turn the photos you take every day into a short “montage” video complete with dates. Today, “montage” generally refers to a film editing technique where multiple short shots are rapidly stitched together to tell a story or move a narrative forward.

    Momentum adopts a standard Material 3 design language, with a clean interface, elegant animations, and a UI logic that feels highly intuitive. It’s visually pleasing to use while also being completely approachable. To get started, you simply create a “Project” (such as “Daily Meals” or “Baby”), after which you’ll see a calendar view. All you need to do is remember to casually snap a photo worth preserving and import it into the corresponding date. If you’re worried about forgetting, you can also enable daily reminders within a project.

    But honestly, I don’t think this feature is necessary. When you encounter moments truly worth remembering, you’ll naturally take a photo anyway. Daily reminders end up feeling more like a burden than encouragement.

    Once you’ve imported photos for at least five days, the app automatically starts stitching them together into a video. But if you simply import photos without anything else, the final result may end up looking more like a slideshow presentation. Don’t forget that this is still a “diary” app — it needs a sense of narrative. While importing photos, you can also add short notes or captions, whether it’s a title for the image or simply how you felt at the moment you took it. These fragments of text eventually appear like subtitles in the final video, transforming what would otherwise feel like a passing stream of images into something much closer to your own personal story.

    In addition, when you have particularly vivid memories tied to a specific day or story, you can favorite that day’s photo with a heart. Those photos are then displayed separately within the project.

    Momentum also includes several genuinely interesting features. For example, when documenting your own growth or that of a child, every photo is naturally taken from slightly different distances and angles. To solve this, Momentum integrates Google’s MediaPipe framework, an on-device machine learning component that enables facial scanning and tracking.

    When exporting the final video, you can simply enable the “Stabilize Faces” option in the short film settings, and the app will automatically align every face to the same position within the frame. Once enough photos accumulate, the resulting video becomes surprisingly powerful — every version of “you” remains centered in the frame, while the backgrounds and stories constantly change around you, as if the world itself is rapidly flowing past behind your back. The strong visual contrast creates an almost tangible sense of “participating in the world.”

    When exporting videos from Momentum, you can also customize the number of frames each photo stays on screen, playback frame rate, date format, background color, and even the font. The app requires no account registration, runs entirely offline, and keeps your data private. If you also find it difficult these days to sit quietly and write long diary entries, perhaps this lighter and more effortless way of recording life’s fragments might suit you better. Momentum is currently available as a free download on Google Play and GitHub. The Google Play version requires in-app purchases to unlock additional features, while the GitHub version is fully free — though you can always “buy the developer a coffee” to show support instead.

    App Updates

    • The Fitbit app will be upgraded to Google Health starting May 19, integrating Fitbit / Pixel Watch, Health Connect, Apple Health, Google Fit migration, and medical records.
    • This year’s Swift Student Challenge has concluded, with multiple student developers from China receiving final awards.
  • SSPAI Review | Best New Apps to Try This Week

    SSPAI Review | Best New Apps to Try This Week

    Maestri: A Whiteboard Tool for the AI Agents Era

    • Platform: macOS
    • Keywords: AI, Agent, Terminal

    @Vanilla: To be honest, when I first opened Maestri’s official website, I thought it was just another app trying to ride the AI hype. However, after actually downloading it and using it to complete a small project, I found that Maestri performs quite well in certain scenarios, helping us better leverage AI Agents to get work done. Next, I’ll use a recent investment research project of mine as an example to see what Maestri can really do.

    When you open Maestri, you’ll notice that its main interface is a whiteboard canvas. You can add elements such as terminals, tags, attachments, file trees, portals, formats, and drawings. Among them, the file tree can be thought of as folders, portals as web pages, formats as text boxes, and the rest are fairly self-explanatory.

    Looking at the toolbar at the top of the canvas, in addition to the elements mentioned earlier, there is also a selection tool that allows you to move or resize elements. All buttons on the toolbar have corresponding keyboard shortcuts, usually a single letter key, making them very quick to access.

    Then, at the bottom right corner of the canvas, there are three buttons: floors, minimap, and zoom.

    The floor feature is something Maestri built using macOS system capabilities. It allows you to create multiple floors, essentially independent workspaces. When creating a floor, you can either start fresh or directly duplicate the base layer. In the end, you can merge them or designate one floor as the final output layer—it has a bit of a Git-like flavor.

    The minimap is a thumbnail view of the entire canvas, helping you quickly locate different areas. The zoom function is even more straightforward, letting you control the zoom level using plus and minus buttons.

    Currently, Maestri’s terminal supports Claude Code, Codex, Gemini CLI, OpenCode, and Shell, and you can choose among them when inserting a terminal element.

    When you insert multiple terminals on the canvas, you can connect them with lines, allowing them to communicate with each other. In addition to connecting terminals, you can also link tags and portals to terminal elements, enabling AI Agents to read and edit the content within those elements.

    Maestri actually relies on Maestri Skills to enable communication between AI Agents and to operate on connected tags and portals. As a result, its capabilities are limited to what Maestri Skills support—for example, AI Agents cannot create new notes and write content into them, nor can they establish links with elements like file trees or text boxes.

    Overall, Maestri addresses the issue of frequent context switching and lack of data interoperability when working with multiple Agents. Through its “canvas” approach, it allows multimedia files within a project to be displayed simultaneously. Especially on large-screen devices, it can significantly improve reading and workflow efficiency.

    Maestri is available for free download on its official website. A $18 purchase unlocks unlimited workspaces, authorization for two computers, keyboard navigation, and more.

    Hour by Hour: A Scheduling App with Natural Language Input

    • Platform: iOS
    • Keywords: Scheduling, Natural Language Input

    @ElijahLee: Hour by Hour is a scheduling app developed by an indie developer. Its standout feature is the ability to input schedules using natural language, with the app automatically recognizing event names and time arrangements, making it easy to plan out an entire day.

    The inspiration for the app came from the developer’s experience creating travel itineraries. For example, if you need to catch a flight at 11:30, what time should you arrive at the airport, when should you leave home, and when should you set an alarm? To perfectly organize such a schedule—handling time calculations, convenient input, and event associations within a single app—the developer created Hour by Hour.

    Adding events via natural language input is one of the app’s key features. You can type “Swim at 3pm,” and the app will automatically recognize a swimming session starting at 3 PM. Then, if you input “Leave 45 mins before,” the app will calculate that you should leave at 14:15, and the two events will automatically be linked. By enabling notifications from the top-right corner of the schedule planning page, the app will send reminders when events begin, helping you remember when it’s time to head out.

    When creating a schedule, you can customize the schedule name, choose an icon, and select dates in the future. The app offers a wide range of customization options. For names, you can add both a title and a subtitle; icon choices span categories such as general, weather, transportation, food and drink, social activities, work, and exercise; date selection includes today, any future date, daily, weekdays/weekends, and recurring cycles.

    For frequently repeated trips or business travels, you can quickly duplicate an entire itinerary. Within a single itinerary, you can naturally set up multi-day schedules. You can also assign different colors to distinguish between itineraries. The app also integrates with Apple Calendar to display events. Overall, the feature set is very comprehensive.

    You can download Hour by Hour for free from the App Store. A one-time purchase of 68 RMB unlocks premium features, including unlimited schedules (the free version is limited to three), AI image generation (currently in testing), and more. Natural language input currently supports English only.

    Voicebox: Clone Your Voice

    • Platform: macOS / Windows
    • Keywords: AI, Voice Cloning

    @化学心情下2: Have you ever had this experience: wanting to record your own podcast, but stumbling over your words in front of the microphone, or making mistakes even when reading from a prepared script? This kind of nervousness when facing an audience has troubled content creators like me as well. But in the age of AI, cloning your voice and turning your written scripts into podcast content is no longer difficult. For example, a tool I recently discovered called Voicebox makes it easy for you to “appear” with your voice.

    Simply put, Voicebox is a tool that can clone your voice and generate audio with the same tone. After opening the app, you first need to download a local AI model for speech generation and transcription. For instance, I directly chose the Qwen TTS 1.7B parameter model, though you can select one based on your computer’s hardware and the language you need. Once the download and model loading are complete, you can start voice sampling.

    Before cloning your voice, you need to create or import a voice profile, which will be used to generate audio with the same tone. After clicking “Create Voice,” you’ll enter the recording interface. Paste the reference script into the “Reference Text” field, choose the target language and local model, and then start recording.

    Once the voice profile is created, you can let the local speech model clone the “voiceprint” from your recording. In the “Voice Profiles” section, select the profile you just recorded, then paste the text you want to convert into speech into the input box below. Choose the language, local model, and voice effects, then click the generate button on the right side of the text box. After a short wait, you’ll hear audio generated based on your voice profile.

    The generated audio can also be further processed. For example, you can apply effects—Voicebox offers presets such as “Robot,” “Radio,” “Echo Chamber,” and “Deep Voice.” The “Audio Channels” feature lets you manage output devices and channels. In “Settings” under “Generation,” you can also configure options like automatic chunking limits, fade-in and fade-out between segments, and audio normalization.

    Beyond generating individual audio clips, Voicebox can also combine multiple audio segments into a story to create a complete audio project. For example, you can import multiple voice profiles with different styles and turn an eBook into an audiobook.

    You can download Voicebox for free from its official website, with support for both macOS and Windows platforms.

    SwiftMTP: A Better Way to Connect macOS and Android via Cable

    • Platform: macOS
    • Keywords: MTP, Android, macOS, File Management

    @克莱德: With the combined push of national subsidies, local AI models, and tools like OpenClaw, many Android users—myself included—have gradually moved from the familiar Windows ecosystem to macOS. If you haven’t fully committed to Apple’s ecosystem, or simply prefer Android over iOS, transferring files between Android and macOS is something you’ll inevitably have to deal with.

    For small daily files, we do have wireless solutions like LocalSend or Blip. But for syncing media libraries or handling large file imports and exports—the “heavy lifting”—a wired connection is still the way to go. And wired options are actually quite limited. If you don’t want to spend big money on simple tasks, nor bother with outdated tools like HandShaker (which hasn’t been updated in years) or the rather plain-looking OpenMTP, you might want to try SwiftMTP, brought to us by SSPAI contributor @Neighbor_Z.

    From my less-than-a-year experience using a Mac, anything with “Swift” in its name tends to feel very “native,” and SwiftMTP is no exception. Compared to OpenMTP, which I had been using before, SwiftMTP adopts a UI design more in line with the visual style of macOS 26 Tahoe. It also embodies the lightweight and responsive nature of native Swift apps (with an installed size of around 15MB, as checked via mole). On top of existing open-source MTP backend solutions, it fixes several key performance and functionality issues. For example, in similar tools, transferring files or folders sometimes led to encoding problems when filenames contained emoji or extended CJK characters, resulting in garbled text or even missing files. SwiftMTP improves the backend encoding logic, making it more reliable—especially for users working with Chinese-language filenames.

    In terms of user experience, SwiftMTP offers favorites and device management in the sidebar. The favorites section comes preloaded with commonly used directories such as Photos, Bluetooth, and Downloads, and you can also add frequently used folders from the right-hand pane. If you manage multiple Android devices, you can connect and control several devices simultaneously via the bottom section.

    On the performance side, SwiftMTP improves the file traversal logic, significantly reducing the time previously required to prepare for file transfers. Transfer speeds are noticeably better than similar tools, and you can cancel transfers at any time. Also worth mentioning is the device information panel on the right—it lets you clearly see the connection protocol and transfer speed between your device and Mac. In scenarios involving long-duration, high-speed file transfers, having this kind of visibility is reassuring.

    SwiftMTP feels like an enhanced and polished version of existing macOS + Android MTP solutions. With its native design and more stable, feature-rich transfer experience, it quickly became my go-to replacement for OpenMTP—a must-have app for macOS setups. The only drawback I’ve noticed so far is that the preview view in the right-hand browsing pane is still somewhat limited at this stage.

    You can download SwiftMTP for free from GitHub.

    Haven: An Open-Source All-in-One SSH Tool

    • Platform: Android
    • Keywords: Remote, SSH, VNC, RDP, Development

    @大大大K: If you ask what’s trending lately, it’s definitely “raising shrimp” and “raising horses.” I set up an Ubuntu Server virtual machine on my NAS and deployed OpenClaw and Hermes Agent just to experiment. But they’re not always well-behaved—sometimes they inexplicably break themselves. Whenever that happens, I have to check the gateway status or manually fix things. Most of the time, though, it only takes a few commands. Booting up a computer just to SSH in feels like overkill, so I found Haven, a tool that lets me SSH remotely right from my phone.

    Although it’s an SSH client, Haven doesn’t compromise on aesthetics. It adopts the Material You design and supports dynamic color theming. Functionally, it’s more than just an SSH client—it also integrates a local terminal, supports remote desktop connections via VNC and RDP, and includes file management features. This all-in-one approach really suits my needs, since these are all essential tools for remote operations.

    Using a terminal or SSH on a phone isn’t exactly convenient, and Haven makes several optimizations to address this. For example, terminals often require key combinations, so Haven pins commonly used keys like Tab, Esc, Ctrl, and Alt above the keyboard. It also provides directional controls including Home and End, along with copy-paste shortcuts. Even better, Haven can natively call virtual terminal tools to maintain persistent sessions. If you’ve installed tools like tmux or screen on your remote system, you should definitely enable this feature in settings—it prevents processes from being terminated when the connection drops.

    Beyond basic SSH connections, Haven includes a built-in file browser and SSH key storage, allowing you to interact with the remote file system through a graphical interface. Even more impressively, it supports running a Linux VM directly on your Android device (provided you have a local terminal tool installed), greatly expanding its versatility.

    On the security side, Haven supports fingerprint unlock, screenshot blocking, tunneling, and other features. If you’re connecting to production systems, having these extra layers of protection certainly provides peace of mind. Overall, Haven is an excellent SSH client: open-source, free, and powerful enough for advanced users, while still being easy to use for beginners like me. If you need to manage SSH from your phone, you can download Haven for free from GitHub or F-Droid.

    Gradient Weather: A Beautiful Yet Practical Weather App

    • Platform: Android
    • Keywords: Weather

    @Peggy_: Generally speaking, a weather app is something every mobile operating system comes with by default. Even so, a wide variety of weather apps continue to be developed, each offering its own differentiation—for example, CARROT Weather, known for its sharp wit, or HeWeather, which is trusted by many for its data accuracy. Of course, there is also a category of apps that focus on design as their main selling point, and the Gradient Weather we’re introducing today stands out with its visual appeal.

    When you first open the app, you can choose whether to grant Gradient Weather access to your location. If you prefer not to, you can still add cities by searching for them manually. After completing this step, you can customize the app’s appearance on the onboarding screen—from theme colors to font selection, offering a fair degree of personalization.

    On the main interface, in addition to the most important current temperature, Gradient Weather places emphasis on the hourly forecast for the next 24 hours. You can tap on any specific hour to view additional details such as wind speed, UV index, and humidity. Following that is the more familiar 7-day weather forecast, helping you understand upcoming weather trends.

    Scrolling further down reveals more detailed information for the current day. Gradient Weather adopts a card-based design, combining large text with colorful icons to effectively present different types of weather data. Each category uses a distinct chart style, reducing visual clutter. Of course, if you’re not satisfied with the default layout, you can customize it to prioritize the information you care about most.

    In the settings interface, Gradient Weather provides even more customization options centered around information display. From the size of weather elements on the home screen, to the layout of future forecasts, to the number of days shown—you can adjust everything. The app also lists its data sources in the settings, making it easy to assess their reliability. A particularly clever touch is the built-in collection of weather-themed app icons: you can either choose your favorite manually or let the icon change automatically based on current weather conditions.

    In addition, Gradient Weather offers different notification types for various weather conditions, which you can later adjust based on what matters most to you.

    If you’re interested in Gradient Weather, you can download it from the Play Store and give it a try.

    Kaori: Keep a Journal of Your Perfumes

    • Platform: iOS
    • Keywords: Perfume

    @Snow: Although China’s perfume market has grown rapidly in recent years, compared to some Western countries, perfume is still a relatively niche consumer product domestically. Enthusiasts often share scent preferences in WeChat groups or on Xiaohongshu, and record their testing notes in local journals or apps like Fragrantica. But when it comes to deciding which fragrance to “wear” before heading out, you probably still have to go through a bit of an internal struggle. Earlier this month, an app called Kaori launched on the App Store—it may help you manage complex scent memories while also easing the dilemma of choosing what to wear.

    Open Kaori and tap the “+” button in the bottom right corner to “Add Perfume,” and you can start registering your collection. Kaori supports customizing details such as perfume name, brand, volume, scent profile, concentration, purchase location, purchase date, usage preferences, related memories, and more. It isn’t limited by third-party databases, so whether it’s a niche fragrance or a custom blend, it can have a place in your personal archive.

    When entering a perfume name or adding an image, the app will automatically call a large model for matching. If a match is found, Kaori will provide suggestions, letting AI fill in part of the data for you. The AI can also analyze uploaded perfume images and isolate the main subject—so long as the shooting angle isn’t too unusual, Kaori can maintain a clean and consistent visual presentation.

    One thing to note is that the “scent profile” field in Kaori does not refer to listing top, middle, and base notes. Instead, it uses the “fragrance wheel” model for classification. For those new to perfumes, if the AI fails to match automatically, you may need to familiarize yourself with how the fragrance wheel works.

    The user preferences set when registering perfumes include three dimensions: season, time of day, and personal liking. These serve as the foundation for Kaori’s intelligent fragrance recommendations. The app combines real-time weather, temperature, and seasonal data from your location to suggest three perfumes best suited to the current moment. You can tap an item to quickly log it, or tap the “+” button in the bottom right to manually select a fragrance based on scent categories.

    In the “Memories” section, you can review all your recent wearing records and understand your latest scent preferences. Within the perfume archive, you can also track usage frequency for each fragrance and gain insight into the contexts in which you tend to favor them—this may also help inform your future purchasing decisions.

    In addition, Kaori offers beautifully designed sharing templates. You can place your daily outfit photos, travel experiences, or casual perfume snapshots into these templates, add your olfactory notes and text, and share them with fellow enthusiasts.

    However, as a newly released app, Kaori still has some limitations. For example, its AI model currently cannot match Chinese names— even for well-known fragrances like Chanel Bleu, you’ll need to input “Bleu” to get a match. Additionally, Kaori does not distinguish between “tested” and “owned” fragrances like Fragrantica does. If, like me, you’re very cautious about purchasing full bottles but have a large collection of samples or decants, Kaori may feel somewhat limited for managing them.

    Kaori includes an in-app subscription: 8 RMB per month or 68 RMB per year. The paid version unlocks unlimited perfume entries, a full calendar feature, watermark-free sharing, and iCloud backup.

    You can download Kaori for free from the App Store.

    App Brief

    • OpenAI has released the GPT-5.5 model, focusing on stronger capabilities in programming, computer operation, and deep research.
    • DeepSeek has unveiled a preview of its next-generation V4 model and open-sourced it simultaneously, emphasizing enhanced reasoning, programming, and Agent capabilities. It supports up to 1 million tokens of context and aims to directly compete with flagship models from OpenAI and Google at a lower cost.
    • The standalone chat app XChat from X is now officially available, allowing login via X accounts. The app is not yet available in mainland China.
    • The read-later tool Matter introduced API and CLI support this month.
  • SSPAI Review | Best New Apps to Try This Week

    SSPAI Review | Best New Apps to Try This Week

    Moods Faster: Log Your Mood in Seconds

    • Platforms: iOS, iPadOS
    • Keywords: mood tracking, emotions, mental health

    @ElijahLee: Ever since Apple Health introduced mood tracking, I’ve been using it to log how I feel each day. Moods Faster, also built around mental health features, focuses on ultra-fast mood tracking. Its core idea is simple: only when logging your emotions is effortless can you stick with it long term. The app is extremely lightweight, coming in at just 9.6 MB.

    The app features a dark-themed design that blends seamlessly with the body of an iPhone 17 Pro. On the home screen, five highlighted capsule-shaped buttons represent five emotional states. By default, they are arranged from left to right as very unpleasant, unpleasant, neutral, pleasant, and very pleasant—mirroring Apple Health’s mood categories.

    In Moods Faster, tapping a mood expands the capsule, and tapping the arrow completes the entry. It takes as little as two taps to log your mood—much faster than Apple Health. The app also offers home screen widgets for quick logging, making up for Apple Health’s lack of widget support.

    If you want to add more detail to your entries, the app provides an Emotions field for more precise descriptions, and a Context field to link mood changes to events in your life or work. Moods Faster supports syncing with Apple Health’s mood data and also offers weekly and monthly mood trends to help you analyze emotional patterns.

    In the app’s settings, you can expand the number of mood options from the default five to seven. It also allows customization of capsule themes and icons, reordering moods from positive to negative, and enabling scheduled reminders. Additional premium features include iCloud sync, full feature unlock, and avatar customization.

    Moods Faster is available for free on the App Store. Paid options unlock premium features such as expanded mood options, additional themes and icons, and home screen widgets. Pricing is RMB 1/month, RMB 11/year, or RMB 28 for a lifetime purchase.

    On This Day Rewind: I Know What You Shot on This Day Years Ago

    • Platforms: iOS / iPadOS / macOS
    • Keywords: photo memories

    @Snow: On This Day Rewind is one of those apps that truly fits the description “small and beautiful.” With a tiny 6.2 MB install size, it focuses on doing exactly what its name suggests: grouping all photos in your system library by date and showing you where you were and what you captured on this day in past years.

    The home screen is clean and “straightforward.” Unlike the system Photos app with its music-backed, heavily edited memory compilations, this app simply presents your memories through a grid of photos arranged in a waterfall layout by year in descending order. That said, On This Day Rewind doesn’t limit itself to just “today.” At the bottom, it features a liquid glass–style date selector and calendar, allowing you to jump to any day and revisit where you went and what you captured.

    As its core “selling point,” the app offers several customization options for the home layout. You can adjust the number of photo thumbnails displayed per row—from one to six—and choose whether years are shown from newest to oldest or vice versa. If you only want to revisit past memories, you can disable the Include Current Year option in settings to hide photos from the current year.

    Tapping a photo opens the detail view, where in addition to the image itself, you can quickly check EXIF metadata and map location, helping you recall what device, settings, and location were used to capture the moment. From here, you can also sync with the system Photos app to favorite or delete images.

    The sharing feature is a thoughtful touch. In Image Share Settings, you can preset captions or date formats, and then share both the text and a photo preview with a single tap from the detail page. However, this feature currently only supports native apps like iMessage and Mail.

    The app includes in-app purchases: you can subscribe for RMB 8/month or make a one-time purchase of RMB 38. The paid version removes the limitation of accessing only the past three years of history and eliminates watermarks on shared images. A 14-day free trial is available. Considering the limited use cases for the sharing feature and some current issues like dropped animation frames and occasional navigation glitches, it’s recommended to try it out before deciding to pay.

    You can download On This Day Rewind for free on the App Store.

    Codex Update: Adds Computer Use, SSH Connections, Built-in Browser, and More

    • Platform: macOS
    • Keywords: AI, AI Agent, Computer Use

    @Vanilla: While Codex arguably offers the best user experience among the “big three” AI model products, it still lags behind Claude in terms of feature iteration, which updates almost weekly. After OpenClaw burst onto the scene earlier this year, both Perplexity and Claude quickly followed with their own Computer Use capabilities. Ironically, OpenAI—which brought OpenClaw developer Peter onboard—only added this feature to Codex in mid-April. Though Computer Use arrives a bit late, let’s take a look at what this major Codex update brings.

    Before using the Computer Use feature, make sure you’ve updated the macOS version of Codex to the latest version, then enable the corresponding plugin under “Computer Use” in the settings panel.

    Back in the chat interface, if you want to manually start a Computer Use instance, simply click the plus button and select “Computer Use” from the plugins. You can then enter commands directly in the chat window. Once authorized, Codex can take control of and operate any app on your macOS system. If Codex determines that a task requires Computer Use, it will prompt you in the chat window to grant permission for specific applications. While Codex is controlling apps, the menu bar clearly shows which applications are currently being handled.

    Notably, the macOS version of Codex introduces a convenient and novel way of granting system privacy and security permissions. Previously, you had to go into System Settings under “Privacy & Security,” click the plus button, and manually add apps. In the new version, Codex allows you to simply drag and drop it directly into the authorization list.

    Once the necessary permissions are granted, Codex uses a virtual cursor to perform various actions—such as writing code in Xcode, editing videos in CapCut, or filling out forms in a browser. More importantly, Codex supports multiple agents running in parallel, operating independently without interfering with each other—or with your own normal usage of the Mac.

    Beyond that, Codex brings a range of additional features in this update. Powered by gpt-image-1.5, its image generation capabilities have improved significantly. Codex can now process GitHub review comments, run multiple terminal tabs simultaneously, connect to remote development machines via SSH, and preview files such as PDFs, spreadsheets, and presentations directly from the sidebar.

    Codex is available for free download on its official website, though the Computer Use feature is currently limited to macOS.

    Road Trip Radar: Bring a Weather Radar Along for Your Drive

    • Platform: Android
    • Keywords: weather, travel radar

    @大大大K: With another long holiday coming up, many people are probably already planning road trips. But driving often means passing through multiple cities or even provinces. Given the vast geography, long-distance travel inevitably comes with complex and changing weather conditions, which may require adjustments to your vehicle and plans. If there were a tool that could show weather changes along your route in real time, you could prepare in advance and avoid disruptions.

    Road Trip Radar really does look like a map app at first glance: a full-screen map interface, oversized icons and buttons, and a standard Material 3 design—all of which make it feel like a minimalist third-party navigation tool. And indeed, it includes some basic map features, such as searching for addresses and nearby facilities (even supporting searches for EV charging stations). However, it lacks full route planning capabilities, so it can’t quite be called a “navigation app.” The only navigation-related elements might be the compass and speedometer displayed on the main screen.

    In reality, the app is positioned as a weather radar tool, designed to help users check upcoming weather conditions during long trips or casual drives. I think it works best as a companion tool to a navigation app. After planning your route in a map app, you can launch Road Trip Radar alongside it—either as a floating window over your navigation app or by having a passenger monitor it on another device. During the drive, it displays real-time nearby radar imagery for rain and snow based on your route, and can even show changes in radar patterns within the next hour.

    A thoughtful feature is its use of concentric circles, which adjust based on your location and map zoom level to indicate distances. This allows you to accurately estimate how far away severe weather is, predict when you’ll encounter it, and plan stops at service areas in advance to prepare your vehicle.

    As for data sources, the app uses MapLibre for map data, providing fairly comprehensive coverage, with some cities even supporting 3D models. Weather data comes from RainViewer, offering relatively accurate rain and snow information for reference. If you’re planning a road trip—or even gearing up for a spontaneous ride on your “motorbike”—you can download it for free via Google Play, GitHub, or F-Droid. Stay safe on the road, and checking the weather in advance is always a smart move.

    macpow: View Real-Time Mac Power Consumption via a TUI Interface

    • Platform: macOS
    • Keywords: command line, system information

    @化学心情下2: Perhaps due to the recent wave of AI coding, CLI and TUI tools have once again come back into the spotlight. Compared to traditional GUI applications, command-line-style tools are often more convenient both to develop and to use. For example, when checking device power consumption, component temperatures, or CPU frequencies on macOS, we used to rely on graphical apps like iStat Menus to access detailed information. Now, however, we can monitor all of this in real time through command-line tools—such as the macpow we’re introducing today.

    Installing the app is very simple. If you use Homebrew for package management, just run the following two commands in the macOS terminal:

    Shell
    brew tap k06a/tap
    brew install macpow

    Then type macpow in the command line to launch and start using it.

    After launching, the first thing you’ll see is a tree-structured view based on your current device. At the top, it shows overall system power consumption along with battery status. The middle section provides detailed real-time data on each component’s temperature and power usage. For instance, on my MacBook Air M4, the SoC section clearly displays the real-time frequency, temperature, and power consumption of both E-cores and P-cores. From the display, it’s easy to see that most of the current power usage is concentrated in the P-cores, while the GPU section below has relatively minimal impact on overall consumption.

    macpow offers very comprehensive hardware monitoring. Temperature readings are available for components such as the CPU, GPU, ANE, memory, storage, display, and even the trackpad. Power consumption tracking also includes external accessories like Thunderbolt ports, network, Bluetooth, and USB devices. For example, one of the higher power-consuming accessories on my setup is a USB 3.1 hub, since my MacBook Air is connected to a monitor through it. Clicking on nodes in the tree view reveals more detailed information, and at the bottom, you can see real-time power fluctuations in a graph.

    The lower half of the interface shows power usage by currently running software. You can view each process’s PID, memory usage, and real-time power consumption. For some applications, you can expand the tree further to inspect details like disk read/write power usage.

    macpow is fully open source and free to use—you can check out the project page for more details.

    June: An Open-Source and Beautifully Designed Journaling App

    • Platform: Android
    • Keywords: journaling

    @Peggy_: At the beginning of this year, I suddenly decided to start keeping a journal. To some extent, it helped me become more aware of my daily life and more attuned to my emotions. But whenever I’m out and about, the traditional notebook format—which requires sitting down properly at a desk—becomes hard to maintain. It seems that combining digital journaling with paper journaling is a better way to cover our needs.

    Today’s app, June, is an open-source journaling tool. In terms of functionality, it is both comprehensive and uniquely designed—so let’s take a closer look. The app’s main interface is divided into several sections: Home, Categories, and Statistics. From the Home page, you can create new entries, view recent journals, quickly search past records, or access drafts that haven’t been saved yet. The Categories page organizes entries by location, people, and tags, making it easier to revisit your journal from different perspectives. The calendar-based Statistics view provides a visual overview of your journaling activity for the month, and you can also see the emojis you’ve added to entries, giving you an at-a-glance sense of your mood on any given day.

    Next, let’s focus on June’s editing interface. It supports rich text editing, with all the expected features such as adding headings of different levels, bold text, and inserting links. In the top-left corner of the editor, you’ll find options to add emojis, attach files, and assign tags. The emoji feature allows you to freely choose from a wide range of symbols.

    June’s attachment feature is where it really stands out. In addition to standard options like adding images, videos, and locations, it also allows you to attach music links. June can parse links from major streaming platforms like Spotify, Apple Music, and YouTube Music, generating a music card that appears at the top of your journal entry. This way, you can not only document your day in words but also revisit your memories later with the accompanying soundtrack.

    Finally, synchronization—an essential feature, since no one wants to lose journals filled with memories and emotions. June currently supports syncing via WebDAV, allowing you to choose a service that fits your preferences. If you’re concerned about data privacy, you can also opt for local backups.

    At this stage, June is already highly polished. In testing, the only issue encountered was that Spotify links were not parsed correctly; otherwise, all features worked as expected. If you’re interested, you can download and try it via its GitHub page.

    App Briefs

  • SSPAI Review | Best New Apps to Try This Week

    SSPAI Review | Best New Apps to Try This Week

    Vibe Island: An AI Agent Assistant Living in the Dynamic Island

    • Platform: macOS
    • Keywords: Dynamic Island, AI Agent

    @Vanilla: In the era of Vibe Coding, products capable of delivering various functionalities are no longer scarce. The massive surge in app review volumes on the App Store this year shows that creating applications has almost become a zero-barrier task. However, apps with taste are still “works of art” in this world—people like me, without programming or design expertise, still can’t create something truly refined.

    In my view, Vibe Island is exactly such a tasteful creation. While using the MacBook notch area to display and interact with AI Agents is nothing new—and there are already open-source, free alternatives on the market—developer Edward Luo has crafted Vibe Island into a beautifully designed, feature-rich product that stands out among its peers.

    After installation, Vibe Island automatically establishes connections with local Agents or terminal applications via hooking, requiring no setup or deployment to start using it. Its functionality can be divided into four main parts: monitoring, authorization, inquiry, and navigation. Let’s go through them one by one.

    In the monitoring section, Vibe Island displays the current session’s title and task overview, allowing you to quickly track the progress of AI Agent tasks through the Dynamic Island. It currently supports ten AI Agents, including Claude Code, Codex, Gemini CLI, Cursor, OpenCode, Droid, Qoder, Copilot, CodeBuddy, and Kiro, as well as 13 terminal applications such as iTerm2, Ghostty, Warp, Terminal.app, VS Code, and Cursor. All of these can be distinguished within the Dynamic Island, helping you clearly manage multi-threaded tasks.

    In the authorization section, Vibe Island displays permission prompts directly in the Dynamic Island, offering options like Deny, Allow Once, Allow Always, and Auto-Approve. You can also confirm actions quickly using keyboard shortcuts. This brings two key benefits: first, you can respond to permission requests immediately, preventing tasks from being paused for too long; second, you don’t need to open the terminal app to grant permissions, so your current workflow remains uninterrupted.

    The inquiry section works similarly to authorization. You can respond to questions from the AI Agent directly within the Dynamic Island, helping guide the agent’s next steps according to your preferences while reducing unnecessary interaction with terminal apps.

    Finally, the navigation feature allows you to click on any item shown in the Dynamic Island to jump directly to the corresponding session in the terminal application, making it easy to view details or input commands.

    In the settings panel, Vibe Island offers several essential customization options. For display, you can adjust the notch style between compact and detailed modes; in the panel section, you can modify font size, completed card height, and maximum panel height; for AI Agents, you can enable or disable detailed activity display.

    In the sound and shortcut settings panel, Vibe Island provides a wide range of options to meet personalized needs.

    As a refined example of Vibe Coding, Vibe Island is a native macOS application written in Swift and optimized for Apple silicon. It is under 50MB in size and avoids the heavy memory usage typical of Electron apps, delivering fast responsiveness and smooth performance.

    Vibe Island is available for download and trial on its official website. The current early-bird price is $14.99 per device, with an additional $10 for each extra device license.

    mynd: Turning Everything Into a Chat-Based Record

    • Platform: iOS
    • Keywords: journaling, logging

    @ElijahLee: Well-known blogger cbvivi recently developed and released a simple app called mynd, which allows users to record their day, moods, thoughts, and all kinds of random notes through a chat-like interface.

    mynd is extremely minimal, with a size of just 5.9MB. Opening the app takes you straight into a conversation screen, where you can record everything as if you were chatting. Each message you send becomes part of the chat history. What’s fascinating is that after some time, your earlier messages will appear as if they were sent by another “you” to your present self. The current “you” can reply or start a new topic—like a dialogue between versions of yourself across time.

    The name mynd comes from a simplified version of “mymind.” Inside the app, there is only you. Like a private tree hollow, you can send anything to mynd, and only you will know. There are no reminders, no streaks, no AI—nothing that might feel like a burden.

    The app supports sending text, images, videos, and voice recordings, all accessible via the “+” button on the left side of the input field. Messages can be edited, quoted, or pinned, making it as convenient as using WeChat. Swipe a message to the right, and the blue chat bubble turns yellow, marking it as a highlight that will stand out in your history. Beyond simple recording, messages can also be turned into to-do items—just double-tap a message to bring up a task circle.

    In the top-right corner, you can access the content and notes categorization page, where mynd automatically organizes entries into pinned, to-do, highlights, excerpts, and more. You can also manually create collections to group notes by theme or category.

    mynd offers home screen widgets and Shortcuts support for quick entry. The widgets can also randomly display past entries and highlights. The app includes multiple color themes, extensive customization options, automatic iCloud backup, and multi-device syncing.

    You can download mynd for free on the App Store. A one-time payment of 18 RMB unlocks premium features, including iCloud sync, full feature access, and avatar customization.

    LibreFit: Fitness, with a Plan

    • Platform: Android
    • Keywords: fitness

    @Peggy_: It all started when I found a barbell in the storage room. Its appearance meant I could finally try some weight training I’d never done before—and perhaps go from beginner to giving up step by step. But when faced with the overwhelming number of training plans out there, I got stuck: how do I remember the sequence, duration, and sets for each workout? I believe many fitness enthusiasts have their own routines and workflows. LibreFit, the app introduced today, helps present these routines clearly on your phone screen, eliminating the need to memorize your training process every time.

    First, you need to create your own workout plan within the app. After naming it and adding notes, you can begin adding exercises. LibreFit’s advantage lies in its built-in library of common exercises. All you need to do is tap and add the ones you need into your plan. Of course, you should still have a clear idea of your training flow to avoid blindly adding too many exercises, which could make your routine ineffective. LibreFit also includes a simple exercise filter, allowing you to quickly find suitable movements based on your ability level, preferences, and target muscle groups.

    Even more thoughtfully, tapping into an exercise’s details reveals descriptions and the muscle groups involved. However, the demo videos are AI-generated and should be used for reference only. It’s recommended to carefully read the key points of each movement and, if possible, train under professional guidance.

    Once you’ve added your exercises, you can move to the workout list to configure sets, duration, and rest intervals for each movement. These settings vary depending on the type of exercise—for example, machine-based workouts usually require weight and reps, while bodyweight exercises may only need reps, and certain movements (like mountain climbers) require duration per set.

    After starting a workout, you can manually mark each set as completed. The app will automatically begin timing the rest interval and display your overall progress at the top. As you accumulate more sessions and training time, LibreFit also generates statistics to enhance visual feedback and help maintain motivation.

    If you’re looking for a fitness-focused app, you can download LibreFit via F-Droid and try it out—it’s completely free.

    Dropzone 5: A Brand-New Interface and New Customization Features

    • Platform: macOS
    • Keywords: file transfer, file operations

    @化学心情下2: The long-standing file staging and processing tool Dropzone has recently received a major 5.0 update. A completely redesigned interface is undoubtedly one of the biggest highlights of this version. Dropzone 5 introduces a Liquid Glass design style inspired by macOS Tahoe, along with a grid-based layout for information, and overall smoother animations during operation.

    The grid system is Dropzone’s most important feature. Through it, you can build specific workflows, and this system has been further enhanced in Dropzone 5. You can switch between different grids via the top dropdown menu, and even create dedicated grids for specific actions, allowing you to quickly switch and execute tasks when needed.

    The grid system is also highly customizable. You can adjust the number of columns, define the position of each row (for example, placing folders or apps in the top row), and most importantly, tailor it to quickly perform the actions you want.

    macOS Tahoe supports custom folder icons and colors, and Dropzone 5 integrates this feature into its grid system. You can sync the adjustments you’ve made to folders in Finder directly within the grid, allowing you to instantly recognize their purpose and function when opening it.

    The final new feature follows the recent CLI trend—Dropzone 5 introduces its terminal tool, dz. You can run dz commands in your desktop terminal to perform Dropzone actions, such as adding files to the Drop Bar or switching between grids. If you have development experience, you can even build automation scripts based on this tool.

    You can download and try Dropzone 5 from the Mac App Store or Setapp. The developer is currently offering a launch discount: new users can get 30% off, while Dropzone 4 users can upgrade to version 5 at half price.

    Infuse 8.4: Automatically Skip Intros and Credits

    • Platform: iOS / iPadOS / tvOS / macOS / visionOS
    • Keywords: media player, media management

    @Snow: Last month, the video player Infuse was updated to version 8.4, introducing two highly practical features: expanded extras content display and automatic skipping of intros and credits. The quotation marks are intentional, as both features had already been gradually tested in previous versions through phased rollouts across different channels—this update essentially “completes” their global implementation.

    As early as version 7.7.x, Infuse had begun supporting intro and credit skipping for third-party services such as Emby, Plex, and Jellyfin. With the help of the TheIntroDB database, this feature is now fully supported across the app. You can adjust it in “Preferences – Playback Settings – Skip Intros and Credits.” However, TheIntroDB’s dataset is still somewhat limited, especially for content from Chinese streaming platforms, where recognition rates remain low. If your videos are not correctly identified, you can register at theintrodb.org and manually submit timing data. Once approved, it will be automatically applied in Infuse.

    Infuse offers four options: On, Automatic (Delayed), Automatic (Immediate), and Off. When set to On, the app displays a floating “Skip” button when it detects intros, credits, or recaps. Tapping it skips the segment; otherwise, the video continues normally, and the button disappears after a short time. With Automatic (Delayed) and Automatic (Immediate), the app skips detected segments automatically. The difference is that Automatic (Delayed) displays the button for three seconds, allowing you to cancel the skip if desired—offering a balance between convenience and control. Personally, I recommend this option.

    When Infuse introduced its redesigned UI in version 8.0, trailers were already presented as a key feature on the detail page. With version 8.4, the app further improves the integration of extras such as behind-the-scenes clips, deleted scenes, and special episodes. These are now automatically displayed alongside the main content or within the same series, rather than appearing as separate entries or nonexistent episodes as in previous versions.

    However, Infuse still relies on file naming conventions and folder structures. Third-party services like Emby typically standardize this upstream. If you manage your own library, you’ll need to use naming rules such as the “Extras” folder or “S00” season to organize content. Unlike some domestic apps, it does not yet use AI to automatically sort and categorize media collections.

    In this update, Infuse finally introduces separate language settings for metadata and poster artwork. In “Preferences – Language,” you can set different languages for audio, subtitles, metadata, and posters. Since many films lack Simplified Chinese posters, previously setting both metadata and artwork to Simplified Chinese often resulted in a mix of Simplified, Traditional, and English posters. Now, you can set poster artwork to English for a more consistent visual presentation.

    Unfortunately, the “original language” option available for metadata matching is not yet supported for poster language settings. If you’re aiming for a fully authentic poster wall, you may need to wait for future updates.

    You can download Infuse for free from the App Store.

    Fucks Given: Give a “Middle Finger” to the Little Things That Don’t Matter

    • Platform: Android
    • Keywords: daily logging

    If you feel exhausted by life or work, it might not actually be life or work itself—but a specific thing that keeps draining your energy. Maybe it’s someone cutting in line during rush hour, an argument on social media, or a spilled bag of takeout soup. These seemingly small “annoyances” can loop in your mind and quietly consume your mental energy. If we don’t handle these everyday disruptions well, each future encounter with similar trivialities will gradually drain the energy that should be making us happier.

    If you want to stop this kind of “mental drain,” why not start by keeping an “account”? Try this bluntly named app, Fucks Given (if you’re familiar with English slang, you’ll get the reference). What first caught my attention was a line from the developer: “Self-love is the greatest middle finger of all time.” In other words, learning to love yourself is the ultimate way to push back against everything that bothers you.

    The purpose of this app is simple: to record how many times you’ve cared about things that weren’t worth it. In essence, it’s a form of “emotional bookkeeping.” Whenever you notice yourself spiraling over something unpleasant or someone you don’t like, just open the app and write down why you’re feeling annoyed. That’s it—there are no complicated features, just pure recording.

    However, I think this act of “logging it” is actually a way to shift your attention. In the past, you might stew over something for hours, but with this app, the moment you record your frustration, you’ve already stepped out of that emotional loop. It’s like reminding yourself: “There I go again, wasting energy on something like this.” Looking back at your “emotional ledger” over a week or a few months, you might realize just how much energy you’ve spent on things that didn’t deserve it.

    Of course, you can also treat Fucks Given as a dumping ground for negative emotions—or even a diary. Anything that drains your energy can be recorded here, helping you process or ignore it, and ultimately care for yourself better. Since these emotions are often private, the app thoughtfully includes password protection, preventing others from snooping through your phone (see, Fucks Given already helps you avoid one unnecessary annoyance).

    The app is open-source, free, ad-free, and very lightweight. You can download it from F-Droid or GitHub, and it’s also available on Google Play under a more “polite” name. If you’ve been feeling irritable or low lately, try using it to confront where your energy is going. After all, our energy is limited—don’t waste it carelessly.

    Tripsy: Calendar Integration and Itinerary Duplication

    • Platform: iOS, macOS, iPadOS
    • Keywords: travel planning, travel logging

    @ElijahLee: The travel planning app Tripsy has released version 3.8, introducing features such as calendar integration and a redesigned itinerary duplication workflow.

    Integration with Apple Calendar has long been a common feature in third-party apps, so Tripsy’s support for it comes a bit late. After updating to Tripsy 3.8, calendar events are enabled by default. Within a trip, you can go to the “Itinerary” page to see Apple Calendar events interleaved with Tripsy’s own travel events. Tapping on a calendar event reveals details such as the event name, notes, location, and links. If the event is a flight, Tripsy will automatically recognize and display flight information.

    In Tripsy, you can also choose which calendars to integrate. However, the toggle for this feature is somewhat hidden—the app does not provide a global switch in the main settings. Instead, you need to go to the “Itinerary” page, tap the “…” button in the bottom-left corner, and enter Preferences to access the calendar configuration page. There, you can enable or disable integration and select which calendars to display.

    The second new feature is itinerary duplication. For frequent business trips or favorite travel routes, this feature allows you to duplicate an entire itinerary or selectively copy specific events into a new trip.

    Within a trip, go to the “Itinerary” page, tap the “…” button in the top-left corner, and select “Duplicate Itinerary.” From there, you can choose which types of events to include—such as flights, accommodations, meetings, or restaurants. You can then modify details like travel dates, total cost, notes, and booking codes, as well as rename the trip and select a cover image. Essentially, all configurable aspects of an itinerary can be selectively copied, offering fine-grained control over duplication.

    In other areas, Tripsy offers both relaxed and compact views on the “Itinerary” page. The compact view can hide location details, and in Preferences, you can disable city names to make the interface cleaner. The new flight selector has also been improved, displaying detailed information such as national flags, full airport names, IATA codes, ICAO codes, and city names, helping users quickly identify flights.

    You can download Tripsy for free from the App Store. A subscription unlocks the Pro version, with flexible pricing options: 38 RMB per month, 198 RMB per year, or a one-time purchase of 998 RMB. Among the new features in version 3.8, advanced calendar integration options are available only to Pro users. Tripsy is also included in Setapp, where subscribers can download and use it at no additional cost.

    App Updates

    Multiple apps in Apple Creator Studio have received updates. Logic Pro adds Dolby Atmos mixing preview, while Pixelmator Pro introduces templates for the iPhone 17 series devices.
    Procreate recently announced that its sixth major version is currently in development and will be released next year. It also confirmed that Procreate 6 will include a Mac version, with further updates to be shared gradually on its official forum.

  • SSPAI Review | Best New Apps to Try This Week

    SSPAI Review | Best New Apps to Try This Week

    Chops: A Local Skill Management Tool for AI Agents

    • Platform: macOS
    • Keywords: AI, Agent, Skill

    @Vanilla: As AI coding tools become more widespread, Skills have emerged as the core mechanism for customizing and extending agent behavior. The problem, however, is that each tool uses its own local storage paths, leaving Skills files scattered across the system with no unified way to manage them—let alone search across tools. Chops is designed to solve this pain point, supporting tools such as Claude Code, Cursor, Codex, Windsurf, Copilot, Aider, and Amp, enabling one-stop Skills management.

    First, Chops comes with a built-in editor that allows you to view, edit, and save Skills files directly, eliminating the need to switch to third-party text editors. In addition to Markdown files, Chops can automatically parse YAML frontmatter (metadata) as well as Cursor’s proprietary .mdc format. Notably, Chops also supports creating new Skills and automatically generates standardized templates (boilerplate) for different tools.

    Second, Chops supports cross-tool organization, search, and synchronization. It can automatically detect Skills on your machine and display them categorized by tool. You can organize scattered Skills from different AI agents using features like favorites and collections, making them easier to access when needed. If you prefer not to organize them manually, Chops also offers full-text search across Skills files, including names, descriptions, and content. Its indexing is powered by macOS FSEvents, meaning that any changes made to Skills files—whether in the terminal or other editors—are reflected in real time within Chops.

    Finally, Chops also supports managing Skills stored on remote servers. Taking OpenClaw as an example, you can connect via server credentials and keys, then use Chops to remotely manage Skills in OpenClaw, including searching, editing, deleting, and installing them.

    If you’re simply looking for a dedicated Skills management tool, Chops is already quite feature-complete. For developers who frequently work with multiple AI coding tools, it’s a productivity tool worth integrating into your workflow. Chops is currently free and open-source—you can download it directly from its official website or compile it yourself from GitHub. For now, it is only available on macOS (requires macOS 15 Sequoia or later).

    PaperKnife+: An Open-Source, All-in-One Local PDF Toolbox

    • Platform: Android
    • Keywords: PDF

    @大大大K: Most smartphones today support generating PDF scans directly from photos, and we’ve grown accustomed to doing this instead of looking for a scanner. However, that convenience often stops at the first step—if you later need to adjust a specific page, or merge and split multiple PDFs, it becomes difficult without access to a computer. Having a mobile app that can handle PDF files with simple operations would make things much easier.

    PaperKnife+ is exactly such a tool. Its UI design is outstanding, with refined details like shadows and icons that feel polished and modern, far from the heavy look of traditional “utility” apps. The feature layout adopts a highly intuitive card-based design, making it both clear and minimal. Although the app does not support Chinese, the English descriptions are simple and easy to understand at a glance. Overall, the experience feels smooth, lightweight, and high-quality.

    PaperKnife+ offers powerful PDF editing capabilities that are more than sufficient for everyday use, covering common needs such as merging files, compression, and page rotation. It also includes many advanced features, such as adding watermarks, signatures, encryption, and even metadata editing. If you need to convert PDFs into other formats, PaperKnife+ has you covered—it supports conversion between PDFs and images, packaging files into ZIP archives, and even extracting text from scanned PDFs, with surprisingly good Chinese OCR performance in testing.

    Of course, for an app that handles private files, data security is critical. PaperKnife+ is open source, and all processing is done entirely offline, which is central to its design philosophy. The developer aims to ensure users can safely handle sensitive documents such as bills, bank cards, and ID information. If you frequently work with PDFs on your phone, you can download PaperKnife+ from GitHub or IzzyOnDroid—definitely a handy tool to have installed.

    brrr: Everything Comes Back to “Notifications”

    • Platform: iOS / iPadOS / macOS
    • Keywords: Notifications

    @Snow: Notifications are an indispensable feature on modern devices. Whether it’s weather updates, calendar reminders, or incoming messages, we’ve grown used to relying on notifications to stay aware of changes. However, even though smartphones can centralize notifications from installed apps and ecosystems can connect notifications across devices, some notifications still remain isolated, and some changes go unnoticed. brrr might help bridge those gaps and give voice to what would otherwise stay silent.

    Opening brrr for the first time can be a bit confusing—the home screen only shows a command line. Tap the “Send Test” button in the top right corner, and you’ll receive a push notification saying “Hello world!” on your installed devices, with copy and share options at the bottom. At this point, if you happen to copy the command line into a terminal or open the official documentation, you’ll start to realize what brrr is really capable of.

    In terms of design, brrr doesn’t execute tasks or handle trigger logic—it focuses solely on “delivering results.” By tapping the copy button, you’ll get a unique key and a push endpoint. As long as you send content to that endpoint via Webhooks, the message will appear on your devices as a system notification. brrr supports customization of notification titles, subtitles, message content, sounds, grouping, delivery modes, and more. You can even include links and set expiration times. As long as your device or service can send HTTP requests, it can use brrr to deliver messages to you.

    Once I understood how brrr works, the first thing that came to mind was syncing notifications from my Synology NAS download tools. All you need to do is go to “DSM → Control Panel → Notification Settings → Webhooks,” create rules for events like download success and failure in tools such as Download Station or qBittorrent, and fill in the push endpoint and content provided by brrr. Then, whenever a download completes or fails, brrr will push the corresponding notification to your devices. If you’re unsure how to structure the JSON payload, the official documentation includes a built-in testing tool where you can fill in fields based on prompts, test the result, and copy it with one click or further customize it.

    Similarly, you can integrate brrr with NAS alerts such as backup completion or Docker service failures, as well as other automation workflows, scripts, or devices—like Home Assistant or router setups. As the final step in an automation chain, brrr allows you to stop manually checking various apps or dashboards and instead receive unified notifications only when needed.

    You can download brrr from the App Store. It currently supports iPhone, iPad, and Mac, offering a 2-week free trial, after which it is available via subscription at ¥8/month or ¥78/year. Since cross-device and cross-service notification orchestration is still a relatively niche need, it’s best to try it out first and decide whether it fits your workflow before subscribing.

    MetaPurge: Don’t Let Your Photos Expose Your Privacy

    • Platform: Android
    • Keywords: Photo Privacy

    @Peggy_: In recent years, reminders about personal privacy have become increasingly common on social media, with one of the most frequent warnings being the risk of privacy leaks when sharing photos. In fact, the everyday images we casually share may contain a significant amount of sensitive information—such as shooting location, date, device name, and more. With the advancement of AI, information that once required manual extraction can now be instantly uncovered.

    To better protect our privacy, we can start by processing our images. Common approaches include blurring sensitive content and removing EXIF data. Today’s recommendation, MetaPurge, is a lightweight tool specifically designed for stripping metadata from photos.

    Using it is very straightforward. After opening the app, tap to add images on the main screen. Once imported, MetaPurge can read all embedded metadata, which means it can also function as an EXIF viewer to some extent. After selecting the images you want to clean, simply tap “Purge” to remove the data. Thoughtfully, MetaPurge does not overwrite the original files—it allows you to save a clean copy to your gallery instead. This ensures that if you ever need the original image with metadata for organizational purposes, it remains intact.

    In addition to processing individual images, MetaPurge also supports batch selection for removing metadata from multiple photos at once. In testing, images processed by MetaPurge were left with almost no metadata—essentially only the file size remained.

    It’s also worth noting that MetaPurge does not request network permissions, and all operations are performed locally, so there’s no risk of your data being transmitted or misused.

    If you’re looking for a tool like this, you can download MetaPurge from F-Droid. It’s open-source and completely free to use.

    Flighty Update: Stay on Top of Airport Intelligence for Better Travel Planning

    • Platform: iOS / iPadOS / macOS / watchOS
    • Keywords: Flight Tracking

    @化学心情下2: What’s the most frustrating part of flying? Flight delays, without a doubt. Delays are often caused by factors such as weather conditions or airport traffic restrictions, making it crucial to understand what’s happening at your departure airport. Flighty’s newly introduced Airport Intelligence feature provides a clear view of the reasons behind delays and can even help predict when disruptions might ease.

    In the airport information panel, you can view today’s overall flight activity, including average delay times, real-time weather, overall departure and arrival delay rates, flight cancellations, as well as hourly delay trends and weather changes.

    Further down the page, you’ll find insights into airline activity and flight density at the airport, along with rankings of top destinations and transit hubs. Taking Nanjing as an example, the busiest destinations currently are Guangzhou Baiyun Airport and Shenzhen Bao’an Airport, while China Eastern Airlines operates the highest number of flights.

    By tapping the “Departures” button in the lower-left corner, you can see the overall delay situation for departing flights that day, along with detailed delay durations for each flight. Tapping into an individual flight reveals its full itinerary details. The filter bar at the top also allows you to sort by airline, destination, and more. The corresponding “Arrivals” section offers similar information and functionality.

    Overall, the addition of Airport Intelligence significantly enhances Flighty’s usefulness for travel scenarios. It helps users better understand airport conditions before departure and anticipate potential delays in advance. If you’re interested, you can download Flighty from the App Store. Airport Intelligence is available with the Pro plan, and you can also explore sample real-time flight data on Flighty’s official website.

    App Updates

    Inoreader has introduced Automated Intelligence Reports, allowing users to customize and receive automatically pushed content briefs based on time, topics, and other filters.
    Google Translate (iOS): The real-time translation feature for headphones is now officially available, supporting 70 languages including English, Chinese, Japanese, Korean, French, German, and Spanish. It also aims to preserve the speaker’s tone, accent, and rhythm during translation, making conversations feel more natural.
    VSCO AI Lab (Web): Adds five new features, including “Dehaze,” “Remove Artifacts,” “Hair Adjustment,” “Photo Restoration for Aging Images,” and “Scene Simplification.”

  • SSPAI Review | Best New Apps to Try This Week

    SSPAI Review | Best New Apps to Try This Week

    Welcome to this episode of SSPAI Review. You can use the table of contents to quickly jump to the sections you’re interested in. If you’ve discovered other apps worth checking out, or topics you’d like us to cover, feel free to join the discussion in the comments.

    Beam Browser: A Dedicated Browser Built for iPad

    • Platform: iPadOS
    • Keywords: Browser

    @ElijahLee: Beam Browser is a brand-new browser app designed specifically for iPadOS. It aims to transform the iPad browser into a productivity tool, featuring a sidebar layout, workspaces, AI support, and deep integration with iPad’s touch interactions and keyboard ecosystem.

    In Beam Browser, webpages are arranged vertically in a sidebar. Compared to Safari’s top tab layout, the sidebar better suits large horizontal screens and allows multiple tab titles to be visible at once, making it far more efficient than traditional horizontal tabs. The sidebar also supports auto-hide for a more immersive experience, and can be easily summoned with a swipe gesture. Functionally, it includes advanced features such as pinning tabs, drag-and-drop sorting, and nested folders.

    Beam Browser also introduces a Space (workspace) feature within the sidebar, somewhat similar to Arc. Users can create dedicated workspaces for different scenarios such as work or personal browsing. Each workspace operates as an independent environment with its own tabs, history, and cache. The app offers a wide selection of icons and allows custom colors to help differentiate between spaces.

    The app includes a Command Bar, accessible via the shortcut Command – T. Similar to Spotlight, it allows users to search the web, switch spaces, invoke AI, or execute specific actions directly. This is supported by robust keyboard and shortcut integration—Beam Browser’s shortcuts closely mirror those of macOS, making actions like opening/closing tabs, searching, and refreshing feel familiar to Safari users. It also introduces new commands, such as using the “@” symbol to quickly search across engines like Google or DuckDuckGo.

    Beam Intelligence can be activated with Command – J. Built on Apple Intelligence, it enables users to interact with webpages through AI, offering features such as summarizing content, analyzing key points, explaining concepts, and extracting information. Users can also switch to third-party large language models, including Claude, Google, and OpenAI.

    In addition, the app includes practical features such as built-in ad blocking, local data storage, webpage hover previews, iCloud sync, forced dark mode, reading mode, and webpage translation. Overall, Beam Browser delivers a powerful and thoughtfully designed browsing experience tailored for iPad. It is available on the App Store, priced at 28 RMB.

    SnapSafe: A Spy-Level Privacy Camera App

    • Platform: Android
    • Keywords: Camera, Privacy

    @大大大K: There are always a few photos on your phone that need extra protection—ID photos, private life moments, or even screenshots that could impact your work. If these are stored normally in your system gallery, a careless tap or a malicious app could expose them, leading to awkward or even serious consequences. SnapSafe, an open-source encrypted camera app, provides robust protection across every stage—from capture/import to storage and sharing.

    Note: SnapSafe disables screenshots. The images shown below are sourced from F-Droid and may differ from the latest version.

    For any privacy-focused app, the most important question is whether it introduces any risk of data leakage itself. SnapSafe eliminates this concern at the root by completely bypassing network permissions at the system level. This means no telemetry, no background uploads—in short, it never sends data externally under any circumstances. Additionally, SnapSafe blocks Android’s system backup from accessing its data, so even if you enable Google’s automatic backup, photos stored in SnapSafe will never be uploaded to the cloud in any form.

    SnapSafe allows you to take photos and videos directly, as well as import from your existing gallery. All captured or imported content is encrypted and stored داخل the app’s own isolated storage, completely separate from the system gallery. When sharing images, SnapSafe automatically strips EXIF metadata such as device information and timestamps, and can randomize file names to prevent reverse identification. In the app settings, you can also adjust how location data is handled during sharing—choosing between precise location, approximate location, or no location data at all, offering flexible control.

    Another standout feature is automatic face detection and blurring during sharing. Officially, this is meant to prevent identity tracing through facial recognition. In practice, it can also double as a convenient image editing tool, especially since many of us have already shared facial photos elsewhere.

    Access to SnapSafe requires a separate password. Notably, it also includes a feature called a “duress password,” similar to those found in some smart locks. By entering a predefined special PIN, the app will silently delete all stored photos in the background, while the interface appears unchanged. You can also mark certain “decoy photos” in advance, which will remain after deletion to create a more convincing illusion. That said, scenarios requiring such a feature are likely quite extreme—but the concept itself is undeniably clever.

    SnapSafe is open-source and free. If you’re looking for a secure way to store photos and videos with peace of mind, you can download it from GitHub or F-Droid and give it a try.

    Comet for iOS: AI Browsers Reach Mobile—Even More Important Than Desktop

    • Platform: iOS / iPadOS
    • Keywords: Browser

    @Vanilla: In my view, AI browsers have greater potential on mobile than on desktop, for a simple reason: desktop environments offer higher operational efficiency—we can quickly achieve our goals using a mouse and keyboard. On mobile, however, we seek simpler ways to accomplish similar results, relying on touchscreens and voice input to approach desktop-level productivity.

    It has to be said that while Perplexity’s AI models may not be the most eye-catching, its product direction and execution quality are excellent, showing a strong understanding of user needs. The newly released Comet for iOS follows the same philosophy. In terms of functionality, the iOS version of Comet largely mirrors its desktop counterpart—so let’s take a closer look.

    Unsurprisingly, Perplexity has brought its core AI Assistant to Comet for iOS. When browsing any webpage, you can tap the assistant button at the bottom of the tab to activate it. The AI assistant understands the content of the current page and can answer questions, generate summaries, or extract key information based on your queries.

    My favorite feature of Comet for iOS is its voice mode. When interacting with the AI assistant, you can switch to voice input, eliminating the inefficiency of typing on a touchscreen and enabling faster, more natural information exchange.

    Comet also recognizes that users don’t always need AI-generated results when searching. On mobile, it introduces a hybrid search mechanism.

    When you search for simple, straightforward queries, Comet directly uses Google Search to display results. For more complex queries, it switches to Perplexity’s AI search engine for deeper research—scanning multiple sources, extracting useful information, and generating cited summaries to provide more comprehensive answers. Within the deep research view, you can also switch to source and image tabs to explore additional relevant content.

    Compared to the desktop version, Comet for iOS lacks browser extension support, which naturally limits its extensibility. Additionally, all browsers on iOS are required to use the WebKit engine, which differs from the Chromium engine used on desktop and may result in performance differences—something to be expected.

    Comet for iOS is available for free on the App Store (in select regions). Pro users can unlock models such as Claude Sonnet 4.6, GPT-5.4, and Gemini 3.1 Pro, while Max users gain additional access to Claude Opus 4.6.

    Readwise CLI: Manage Your Read-Later Content via the Command Line

    • Platform: Windows / macOS
    • Keywords: Read-it-later, AI, CLI

    @化学心情下2: With the recent rise of AI agents, using the CLI (command-line interface) to operate various apps through AI has gradually become a hot topic. The long-standing read-it-later tool Readwise has recently released its own CLI utility, allowing users to search their library, save URLs to Reader, and perform a range of actions directly from the command line—or even let AI handle these tasks for you.

    The installation process is quite simple. First, make sure you have a Readwise account. Then, in your terminal, run: npm install -g @readwise/cli to install it. After that, enter readwise login to complete the authorization process. When you type readwise again and see the following TUI interface, it means the installation was successful.

    Although the official documentation provides many CLI examples, the TUI interface makes it easy to operate step by step. For example, to search saved documents, use the arrow keys to select “Search Documents,” then enter your keyword directly in the interface and press Enter. The tool will search your inbox and return the most relevant entries, which you can open by pressing Enter. During search, you can also press the Tab key to add filters such as document ID, tags, or URLs, helping you locate specific content more precisely.

    One of the most interesting features in the CLI is saving articles via URL. Select “Create Document” using the arrow keys, then press Tab to choose options. For example, if you want to add a URL to your Reader inbox, select “url,” paste the link, and press Enter to complete the process.

    Once finished, the CLI will return a document ID and its corresponding link, indicating that the article has been successfully added. You can click the link below to view the processed content.

    Similarly, through the CLI, you can list documents in your inbox and view your highlights. To list inbox items, choose “List Documents,” press Tab to select “location,” then choose “new.” After confirming, you’ll see your inbox articles sorted by the order they were added.

    To view highlights, return to the main menu and select “List Highlights.” You can press Tab to apply filters or simply press Enter to display all highlights.

    Beyond these commonly used features, there are many other practical functions not covered here due to space constraints. After installing Readwise CLI, you can explore them yourself. You can even use official Skills to let tools like Claude Code assist with summarizing content or recommending reading materials. If you’re using the Claude desktop app or other AI tools, you can also install MCP services to connect them with your Readwise account.

    For more information, you can visit the official website to learn more about Readwise CLI.

    Momentum: Capture One Photo a Day to Record Life’s Small Moments

    • Platform: Android
    • Keywords: Daily journaling

    @Peggy_: Everyone has their own way of documenting life—some like to share everything in real time on social media, while others prefer quietly writing in a journal. No matter the method, the act of recording itself carries meaning, helping us push back against the seemingly repetitive nature of everyday life.

    You’ve probably seen people online documenting changes by taking one photo every day. With long-term consistency, time itself becomes a sculptor, shaping something meaningful. The app Momentum is designed to help you capture these subtle daily changes—whether of yourself or the world around you.

    Taking the growth of a plant as an example, you first create a new project in Momentum, adding a name and description. Once the setup is complete, you can enter the project interface, tap on the current date, and select the image you want to record. It’s worth noting that Momentum doesn’t take photos itself—it organizes images already stored on your device, so you don’t need to worry about it consuming additional storage space.

    After adding a photo, you can write a description or mark meaningful images as favorites. If you’re worried about forgetting, you can also set reminders within each project to help maintain consistency. Momentum will notify you based on your chosen interval—for example, you can set a reminder every 48 hours.

    As your collection grows (five photos or more), you can use the app’s “Create Montage” feature to turn your images into a fast-playing video. Playback settings can be adjusted afterward. If you’re documenting a person, you can also use the built-in face recognition feature to identify specific faces and apply additional settings, ensuring smoother and more consistent results in the generated video.

    If you’re interested in Momentum, you can download it from the Play Store. The app itself is free, with additional features available via subscription—$0.99 per month or a one-time purchase of $3.49.

    Recordly: A “Combo” Approach to Screen Recording

    • Platform: macOS / Windows / Linux
    • Keywords: Screen recording

    @Snow: Screen recording is both simple and complex. It’s simple because almost any third-party app—or even built-in system tools—can start recording with a single click. But it becomes complicated when you want to create tutorials or product demos. Recording is just the beginning—you still need to spend significant time on post-production: syncing voiceovers, zooming into key areas, refining mouse movements, adding click animations… Often, this requires juggling multiple apps across a heavy workflow. What Recordly aims to solve is exactly this—offering a “combo” solution that simplifies the entire process within a single app.

    Getting started with Recordly is straightforward. On macOS, for example, its workflow is quite similar to QuickTime. After launching, a floating toolbar appears, where you can choose to record the full screen or a specific app window, adjust audio input, camera sources, and countdown delay. Once everything is set, click the red record button to begin. During recording, Recordly captures mouse movements and interactions, and automatically adds mouse trails, click animations, and Screen Studio–like auto-zoom effects in the project file, ensuring that key interactions always stay in focus.

    After recording, Recordly provides a lightweight editor with a timeline and preview window for more detailed adjustments. It supports basic editing tasks such as trimming, speed adjustments, and aspect ratio changes. Its interaction logic differs slightly from traditional video editors—when you apply trimming or speed changes, colored segments appear on the timeline to indicate the affected areas. Additionally, Recordly allows you to adjust global zoom levels, add annotations, and include background music.

    By clicking the three buttons on the left side of the preview window, you can switch between different editing panels. From top to bottom, these correspond to visual effects, mouse cursor settings, and camera controls—three key elements for presentations. In visual effects, you can adjust background, frame borders, cropping, and motion blur for zoom transitions. In the cursor panel, you can toggle visibility, adjust cursor size, smooth movement, and customize click animations.

    If you recorded webcam footage alongside your screen, Recordly places it by default in a floating window at the bottom-right corner of the video, automatically scaling it based on the content. You can adjust its visibility, position, size, and shadow intensity in the camera panel. Even if you didn’t record webcam footage initially, you can link it to your screen recording here afterward.

    Once editing is complete, Recordly allows you to export files in multiple resolutions as MP4 or GIF, depending on your needs. One drawback is the lack of subtitle support—if you need captions for presentations, you may have to rely on AI tools or other editing software.

    Recordly still has quite a few bugs. For example, I encountered issues where it couldn’t use AirPods for audio recording, and enabling the webcam sometimes caused interaction glitches during recording. However, considering that it is open-source and completely free, I’m still happy to use it for relatively simple projects. Recordly currently supports Windows, macOS, and Linux—you can download it from the official website or its GitHub page.

    App Updates

    • Apple acquires MotionVFX, a well-known marketplace for video editing plugins.
    • According to reports, Apple had previously considered acquiring Lux, the developer behind the popular iOS camera app Halide. After negotiations fell through, one of Lux’s co-founders, Sebastian, announced that he had joined Apple’s design team. Recently, Lux’s other co-founder, Sandofsky, alleged that Sebastian provided Apple with Lux’s confidential materials and source code, and is preparing to file a personal lawsuit against him. Source