Web app: the recommended starting point
Opens in any modern browser with nothing to install — the most complete features and the fastest updates. Mobile browsers get the full experience too, and "Add to Home Screen" gives a near-native fullscreen feel. When in doubt, start with the web app.
Windows / macOS desktop: available now
Download installers from GitHub Releases (.exe installer for Windows, .dmg for macOS, both in Chinese, English, Japanese and Korean). The desktop builds add native touches like a system tray and lock screen, suited to heavy, always-on use. Note they're not in app stores yet — on first launch, follow the system security prompt to allow them; see the Windows and macOS install guides for details.
Android: beta APK sideload
GitHub Releases offers a beta APK — download and install directly (you'll need to allow "install from unknown sources" in system settings). It's a beta, so feedback on any issues is welcome; if you'd rather not sideload, the mobile browser plus "Add to Home Screen" works great too.
iOS and the WeChat mini program: coming soon
The iOS client and WeChat mini program aren't released yet. iPhone users are best served today by opening the web app in Safari and using "Add to Home Screen" — the experience is already close to native. Release progress will be posted in the changelog and on the download page.
Self-hosting: full autonomy
To keep your data 100% on your own machine, self-host the complete Enclave with Docker Compose (MIT-licensed, commercial use allowed). After deployment you access it through the browser just the same, and the desktop and mobile entry points are unaffected.
Related questions
Which devices / platforms does Enclave support?
Enclave is a browser-based web app that works right out of the box, with desktop apps for Windows, macOS, and Linux, plus mobile experiences for iOS and Android. Modern browsers (recent versions of Chrome / Edge / Safari / Firefox) need no installation at all.What do I need to self-host Enclave? Do I need a GPU?
Not necessarily a GPU. If you use cloud model APIs (OpenAI, Anthropic, etc.), an ordinary server or home machine that can run Docker is enough — inference happens in the cloud, and your machine only runs the app and database. You only need the corresponding VRAM and compute if you want offline inference with local models (Ollama / vLLM).Can I self-host Enclave? Is it hard?
Yes, and it's about as hard as running an ordinary web service. If you've used docker compose, three steps get you your own instance: clone the repo, copy .env, and docker compose up. The API, frontend, database, and vector index all run on your own machine.