🐑 LambChat

An open-source, production-ready AI Agent platform for building, running, and sharing real tool-using agents

English · 简体中文 · Documentation · Contributing

📸 Screenshots

🌟 Why LambChat

LambChat is built for teams who want more than a chatbot UI. It gives you a complete AI Agent system with model management, MCP connectivity, skills, storage, sharing, approvals, and deployment-ready backend/frontend infrastructure in one project.

• Built for real execution — agents can reason, call tools, use sub-agents, stream progress, and work with human approval when needed.
• Ready for operations — includes auth, RBAC, encrypted secrets, tracing, health checks, sandbox integration, and distributed config sync.
• Designed for extensibility — custom agents, MCP tools, skills, model providers, channels, persona presets, and storage backends can all be extended cleanly.
• Product-grade UX — polished chat UI, file previews, project folders, sharing, feedback, responsive layouts, and multilingual support.

🎬 Use Cases

🏗️ Architecture

✨ Features

• deepagents Architecture — Compiled graph runtime with fine-grained state management
• Multi-Agent Types — Core, fast, and search agents
• Plugin System — @register_agent("id") decorator for custom agents
• Streaming Output — Native SSE support
• Sub-agents — Multi-level delegation
• Thinking Mode — Extended thinking for Anthropic models
• Human-in-the-Loop — Approval system with countdown timer, auto-extension, and urgent-state styling
• Persona Presets — Reusable persona configuration with permissions and runtime binding

• Multi-Provider Models — OpenAI, Anthropic, Google Gemini, and Kimi
• Full CRUD — Create, edit, delete, reorder, and batch import models via UI
• Channel Routing — Route the same model through different channels with model_id
• Role-based Access — MODEL_ADMIN permission and per-role model visibility
• Cross-session Memory — Native MongoDB-backed memory system
• Dual Skills Storage — File system plus MongoDB backup
• GitHub Sync — Import custom skills from GitHub
• Skill Marketplace — Browse, install, publish, and manage skills in bulk

• System + User MCP — Global and per-user MCP configuration
• Encrypted Storage — API keys encrypted at rest
• Dynamic Tool Caching — Cache MCP tools with manual refresh
• Multiple Transports — SSE and HTTP
• Permission Control — Transport-level access policies
• Sandbox Integration — Daytona and E2B execution support
• Built-in Tools — File reveal, project reveal, upload URL, env vars, audio transcription, persona preset tools, and more

• File Library — Browse revealed files with code preview, favorites, and project-based filtering
• Rich Previews — PDF, Word, Excel, PPT, Markdown, Mermaid, Excalidraw, images, and video playback
• Project Folders — Organize sessions into projects with drag-and-drop
• Session Sharing — Generate public share links for conversations
• Feedback — Thumbs rating, text comments, session linking, and run-level stats
• Notifications — In-app notification storage and delivery hooks

• Realtime — Redis + MongoDB dual-write, WebSocket, auto-reconnect, and shared-session updates
• Security — JWT, RBAC, bcrypt, OAuth (Google/GitHub/Apple), email verification, CAPTCHA, and sandbox controls
• Observability — LangSmith tracing, structured logging, health checks, and distributed memory diagnostics
• Channels — Native Feishu integration plus an extensible multi-channel architecture
• Frontend Stack — React 19, Vite 6, TailwindCSS 3.4, dark/light theme, rich content rendering, and responsive multi-device layouts
• i18n — English, Chinese, Japanese, Korean, and Russian

⚙️ Configuration

Multiple setting categories can be configured through the UI or environment variables:

🚀 Quick Start

Prerequisites

• Python 3.12+ · Node.js 18+ · pnpm · MongoDB · Redis

Setup

git clone https://github.com/Yanyutin753/LambChat.git
cd LambChat

# Docker (recommended)
cd deploy && cp .env.example .env   # Edit with your config
docker compose up -d

# Or local development
cp .env.example .env   # Edit with your config
make install-pnpm      # Install pnpm if not present
make install && make dev

Edit the .env file with the following recommended settings:

# Recommended: Set a stable JWT secret (auto-generated on each restart if unset, invalidating existing sessions)
JWT_SECRET_KEY=your-stable-secret-key

# Recommended: Set MCP encryption salt (auto-generated on each restart if unset, invalidating saved MCP configs)
MCP_ENCRYPTION_SALT=your-stable-encryption-salt

# Optional: Configure MongoDB connection
MONGODB_URL=mongodb://localhost:27017
MONGODB_DB=agent_state
MONGODB_USERNAME=admin
MONGODB_PASSWORD=your-mongo-password

# Optional: Configure Redis connection
REDIS_URL=redis://localhost:6379/0
REDIS_PASSWORD=your-redis-password

::: tip LLM models are configured through the Model Config UI after deployment — no environment variables needed. :::

Open http://localhost:8000

Code Quality

make format       # Format (ruff format)
make lint         # Lint (ruff check)
make typecheck    # Type check (mypy)
make check-all    # Run all checks (lint + typecheck + test)

Project Structure

src/
├── agents/         # Agent implementations and runtime graphs
├── api/            # FastAPI routes, admin endpoints, middleware
├── infra/          # Core services: auth, llm, mcp, tools, storage, tasks, sharing, memory
├── kernel/         # Schemas, config, constants, and shared types
└── skills/         # Built-in skills
frontend/
├── src/components/ # UI components, panels, and landing sections
├── src/hooks/      # Frontend hooks
├── src/i18n/       # Locale files
└── src/styles/     # Shared styles and design tokens
tests/              # Backend and integration tests
deploy/             # Docker deployment assets

⭐ Star History

📄 License

MIT — Project name "LambChat" and its logo may not be changed or removed.

LambChat is built for people who want AI agents that can actually do the work.

Created by Clivia

GitHub · Email · 中文 README

WeChat for deployment help, product feedback, and collaboration