byob releases local-first desktop AI agent
Understand this story
scronkfinkle releases byob, a local-first desktop AI agent that does not depend on Electron and does not bundle an inference engine or require an account; it can connect to llama-server, Ollama, LM Studio, vLLM, or any OpenAI-compatible endpoint, and read and write files in folders, run code, and generate spreadsheets, charts, documents, and small apps. The macOS build has not yet received Apple developer signing, so after downloading via a browser, the first launch will be rejected by the system: you can first try to open it once, then go to "System Settings → Privacy & Security" and choose "Open Anyway" (on macOS 14 and earlier, right-click to open), or run xattr -dr com.apple.quarantine /Applications/byob.app. The Linux version does not require a GUI toolkit; file dialogs are implemented via the XDG desktop portal or zenity, and when neither is available you can drag files into the window; rendering uses the system OpenGL (Mesa).
AI overview based on source reports · Updated 1 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIShow HN: A local-first AI agent for the desktop, no Electron, any LLM endpoint
byob is a native desktop AI agent that connects to any OpenAI-compatible endpoint (llama-server, Ollama, LM Studio, vLLM or hosted APIs) and works in a folder, reading and writing files, running code, and building spreadsheets, charts, documents and small apps beside the chat. It is a single program for Linux, macOS and Windows that draws its own GPU interface without Electron, with a browser UI compiled to WebAssembly, approval cards with diffs, per-turn undo, and a plugin system it can use to write and fix its own plugins. It ships as a roughly 60 MB download (13 MB slim build) and is licensed under MIT OR Apache-2.0.
Activity for this story
Not enough continuous observations to show a trend yet.