Build, run, and share AI agents that actually finish work
LambChat is an open-source AI Agent platform: multi-model chat, MCP tools, a skills engine, persistent memory, and production-ready deployment — in one self-hostable stack.
What LambChat can do
Agent Runtime
Deep agent graphs with sub-agents, thinking mode, streaming output, and human approval for risky actions.
MCP & Tools
System-level and per-user MCP servers, encrypted secrets, and sandboxed code execution on Daytona, E2B, or CubeSandbox.
Memory & Skills
Cross-session memory, a skill marketplace, GitHub-synced skills, and reusable persona presets.
Multi-Model Chat
Bring your own keys for Claude, GPT, Gemini, and more — with SSE streaming, multimodal input, and document processing.
Full-Stack Client
React 19 web app, Capacitor mobile apps, Tauri desktop app, and installable PWA — one backend for all of them.
Production Ready
JWT auth with RBAC, realtime sync, scheduled tasks, usage tracking, and Docker / Kubernetes deployment recipes.
Why LambChat
Most agent products stop at “chat with tools.” LambChat is designed for the longer path: configure models, connect tools safely, let agents create artifacts, persist useful context, share results, approve risky actions, and deploy the whole system for real users — self-hosted, open source (MIT), and bilingual documentation included.
Under the hood
Python 3.12 + FastAPI +
LangGraph / deepagents · MongoDB +
Redis + arq ·
React 19 + TypeScript +
Vite · Deploy with Docker or
Kubernetes. English, 中文, 日本語, 한국어, and
Русский interfaces.