Vibe Coding Discoverajean
View on GitHubRun your AI models at home in one binary: chat, persistent memory, web access, browser control, MCP tools, encryption at rest and end-to-end encrypted remote access. Linux, macOS, Windows. FR/EN docs.
Single Go binary wrapping llama.cpp into a self-hosted AI assistant: chat UI, persistent Markdown memory, terminal/file/web/browser tools, MCP servers, encryption at rest and encrypted remote access. Handles GPU detection, model presets and an OpenAI-compatible endpoint.
Use Cases
Run an AI assistant entirely at home with no cloud dependencyExpose a local OpenAI-compatible endpoint for third-party toolsLet the model use terminal, file, web and MCP tools in agent modeDrive a real local browser to complete web tasksKeep persistent Markdown memory across sessionsChat from a phone via end-to-end encrypted remote tunnelSchedule recurring autonomous tasksCompile llama.cpp with CUDA/ROCm/Metal for the local GPUEncrypt conversations and memory at rest with AES-256Switch between multiple saved model presets
Built With
- Language
- Go
- Frameworks
- llama.cpp · modelcontextprotocol/go-sdk · bbolt · certmagic · webpush-go · crawl4ai · chromedp/CDP · systemd
Tags
local-ai · self-hosted · llama.cpp · gguf · mcp · agent · browser-control · computer-use · persistent-memory · encryption-at-rest · openai-compatible · web-search · cuda · privacy · multimodal · single-binary