An open-source AI Agent platform for building, running, and sharing agents that actually finish work.
English · 简体中文 · Documentation · Contributing
- 🤖 Agent Runtime — Deep agent graphs, sub-agents, thinking mode, streaming output, and human approval
- 🔧 MCP & Tools — System/user MCP, encrypted secrets, sandbox execution (Daytona/E2B/CubeSandbox)
- 🧠 Memory & Skills — Cross-session memory, skill marketplace, GitHub sync, persona presets
- 📱 Full-Stack Client — React 19 web, Capacitor mobile, Tauri desktop, PWA support
- 🚀 Production Ready — FastAPI, auth/RBAC, realtime sync, Docker/K8s deployment
- 🌍 Internationalization — English, Chinese, Japanese, Korean, Russian
LambChat is more than a chatbot UI. It is a full-stack AI Agent system with agent runtime, model management, MCP tools, skills, memory, files, sharing, approvals, scheduled tasks, and production-ready deployment pieces in one project.
| If you want to... | Go here |
|---|---|
| See what LambChat can do | Product Preview and Live Examples |
| Run it quickly | Quick Start |
| Understand the system | Architecture and Feature Map |
| Configure production pieces | Configuration and Deployment |
| Contribute | Development and Contributing |
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.
| Agent Runtime | Tools and MCP | Skills and Memory | Production Infra |
|---|---|---|---|
| Deep agent graphs, streaming output, sub-agents, thinking mode, scheduled runs, and human approval. | System and user MCP, encrypted secrets, tool cache, upload/reveal tools, and sandbox execution. | Skill marketplace, GitHub sync, persona presets, model routing, and MongoDB-backed memory. | FastAPI, React 19, auth/RBAC, tracing, health checks, arq tasks, realtime sync, and deployment assets. |
| Chat and execution | Skills marketplace | Operations console |
|---|---|---|
 Streaming agent work |
 Reusable skills |
 MCP and tools |
 Rich file library |
 Model routing |
 Responsive UI |
View the full screenshot gallery
 Login |
 Register |
 Password Reset |
 Email Verification |
 Registration Pending |
 Chat |
Streaming |
 Share |
 Skills |
Marketplace |
MCP Config |
 Agents |
Models |
 Channels |
Files |
 Persona |
 Memory |
 Notifications |
 Settings |
 Feedback |
 Shared Session |
 Roles |
 Users |
 Tablet |
These shared sessions show the kind of end-to-end work LambChat is built for.
| # | Case | What the agent does | Demo |
|---|---|---|---|
| 1 | Supply Chain PDF Report | Generates a polished PDF efficiency report with charts, benchmark comparisons, and delivery, inventory, fulfillment, and logistics analysis from a single prompt. | View Session |
| 2 | Godfather Fan Website | Builds a responsive English promo site for The Godfather trilogy with a cinematic visual direction, marquee hero section, generated images, and multi-device polish. | View Session |
| 3 | Story Breakdown from Image | Understands visual input, identifies the stories shown in an image, and produces detailed plot-by-plot explanations with multimodal reasoning. | View Session |
| 4 | EV Market Trend Analysis | Turns recent 2025-2026 electric vehicle data into a structured market analysis covering growth, regional performance, and key industry takeaways. | View Session |
| 5 | Batch Game UI Icon Generation | Analyzes one reference image, generates 48 game UI icons across 9 categories, organizes them into folders, and saves the workflow as a reusable skill. | View Session |
| 6 | E-Commerce Product Image Suite | Runs audience analysis, visual strategy, main image generation, lifestyle scenes, detail shots, and combo images for a product keyword and marketplace. | View Session |
| 7 | Multi-Agent E-Commerce Design Team | 4 agents collaborate (creative director, designer, AI image engineer, reviewer) to produce a full set of brand e-commerce product images with strategy, generation, audit, and revision in one session. | View Session |
| 8 | Daily AI Paper Digest (Scheduled Task) | A scheduled task runs automatically every day to search arXiv across 5 research directions (VLA, World Models, LLM Reasoning, Multimodal, Agent), filter the latest papers, and generate a structured trend summary — zero manual intervention. | View Session |
LambChat keeps the product surface and runtime infrastructure in one deployable system:
- Frontend: React 19, Vite, TailwindCSS, PWA workers, Capacitor mobile builds, and Tauri desktop packaging.
- Backend: FastAPI, SSE/WebSocket streaming, auth/RBAC, scheduler, storage services, model routing, and MCP management.
- Agent runtime: deepagents/LangGraph execution, sub-agents, approvals, skills, memory, tools, and sandbox integrations.
- Persistence and queues: MongoDB, Redis, optional PostgreSQL checkpoints, S3-compatible object storage, and arq workers.
Agent Runtime
- deepagents architecture with compiled graph runtime and fine-grained state management.
- Multiple agent types for core, fast, search, and team workflows.
- Plugin registration through
@register_agent("id")for custom agents. - Streaming output with native SSE support.
- Sub-agents for multi-level delegation.
- Thinking mode for Anthropic extended thinking.
- Scheduled tasks with cron, interval, date, manual triggers, and persisted scheduler state.
- Human approval with countdown timer, auto-extension, and urgent-state styling.
- Persona presets with reusable configuration, permissions, and runtime binding.
/goalcommand — attach a rubric-guided objective to any run via/goal <objective>, with optional custom rubrics (/goal <objective> --- <rubric>), SSE event tracking, and auto-dismissal on completion.
Models, Memory, and Skills
- Multi-provider models for OpenAI, Anthropic, Google Gemini, and Kimi.
- Model CRUD for creating, editing, deleting, reordering, and batch importing models in the UI.
- Channel routing to reuse the same model through different channels with
model_id. - Role-based model access through
MODEL_ADMINand per-role visibility. - Cross-session memory backed by native MongoDB storage.
- Dual skills storage with file system storage plus MongoDB backup.
- GitHub sync for importing custom skills.
- Skill marketplace for browsing, installing, publishing, and bulk managing skills.
Tools, MCP, and Execution
- System and user MCP for global and per-user tool configuration.
- Encrypted storage for API keys and MCP secrets at rest.
- Dynamic tool caching with manual refresh.
- Multiple transports including SSE and HTTP.
- Permission control at the transport and role level.
- Sandbox integration with Daytona, E2B, and CubeSandbox.
- Built-in tools for file reveal, project reveal, upload URLs, env vars, audio transcription, persona presets, and more.
Product Surface
- File library with revealed files, code preview, favorites, and project filters.
- Rich previews for PDF, Word, Excel, PPT, Markdown, Mermaid, Excalidraw, images, and video.
- Project folders for organizing sessions with drag-and-drop.
- Session sharing through public conversation links.
- Feedback with thumbs rating, comments, session links, and run-level stats.
- Notifications with in-app storage and delivery hooks.
Infrastructure and Realtime
- Realtime sync with Redis, MongoDB dual-write, WebSocket, auto-reconnect, and shared-session updates.
- Task runtime with local execution or Redis-backed arq queues.
- Security with JWT, RBAC, bcrypt, OAuth, email verification, CAPTCHA, and sandbox controls.
- Observability with LangSmith tracing, structured logging, health checks, and distributed memory diagnostics.
- Channels with native Feishu integration and an extensible multi-channel architecture.
- Internationalization for English, Chinese, Japanese, Korean, and Russian.
git clone https://github.com/Yanyutin753/LambChat.git
cd LambChat
cd deploy
cp .env.example .env
docker compose up -dOpen http://localhost:8000.
Install dependencies:
cp .env.example .env
make install-allRun the backend and frontend together:
make dev-allBackend: http://127.0.0.1:8000 Frontend dev server: http://127.0.0.1:3001
You can also run them separately:
make dev # FastAPI backend: uv run python main.py
make frontend-dev # Vite frontendLLM models are configured through the Model Config UI after deployment. You do not need to put model keys in environment variables for the basic boot path.
LambChat can be configured through the UI and environment variables. Start with .env.example, then set stable secrets before using it with real users.
Runtime settings stored in the database take precedence over environment variables. Environment variables are used as initial values or fallback values only when the corresponding database setting has not been set.
# Recommended: keep sessions valid across restarts
JWT_SECRET_KEY=your-stable-secret-key
# Recommended: keep saved MCP configs decryptable across restarts
MCP_ENCRYPTION_SALT=your-stable-encryption-salt
# Optional: MongoDB
MONGODB_URL=mongodb://localhost:27017
MONGODB_DB=agent_state
MONGODB_USERNAME=admin
MONGODB_PASSWORD=your-mongo-password
# Optional: Redis
REDIS_URL=redis://localhost:6379/0
REDIS_PASSWORD=your-redis-password
# Optional: scheduled tasks
ENABLE_SCHEDULED_TASK=true
# Optional: task execution backend
TASK_BACKEND=arq # local or arq| Category | What it controls |
|---|---|
| Frontend | Default agent, welcome suggestions, UI preferences |
| Agent | Debug mode, logging level |
| Model | Multi-provider model management, per-model config, channel routing |
| Session | Session management, message history, SSE cache |
| Database | MongoDB connection, optional PostgreSQL |
| Storage | Persistent storage, S3/OSS/MinIO/COS |
| Security | Encryption and security policies |
| Sandbox | Code sandbox settings for Daytona, E2B, and CubeSandbox |
| Skills | Skill system configuration |
| Tools | Tool system settings |
| Tracing | LangSmith and tracing |
| User | User management, registration, default role |
| Memory | Native memory system |
| Scheduler | Dynamic scheduled tasks and runtime registration |
| Task Runtime | Local execution or arq queue settings |
make format # Format with ruff
make lint # Lint with ruff
make typecheck # Type check with mypy
make test # Backend tests with pytest
make check-all # Run lint + typecheck + testscd frontend
pnpm run build # TypeScript + Vite build
pnpm run packaged:build # Build packaged frontend assets
pnpm run mobile:sync # Build and sync Capacitor projects
pnpm run package:desktop # Package desktop app assets
cd ..
pnpm run docs:dev # VitePress docs site
pnpm run docs:build.
├── main.py # Uvicorn entrypoint for src.api.main:app
├── src/
│ ├── agents/ # Core, fast, search, and team agent graphs
│ ├── api/ # FastAPI app, middleware, and route modules
│ │ └── routes/ # Chat, auth, MCP, skills, files, scheduler, teams, etc.
│ ├── infra/ # Runtime services: auth, llm, mcp, scheduler, task, storage, memory
│ └── kernel/ # Settings, schemas, config definitions, and shared types
├── frontend/
│ ├── src/ # React app source
│ │ ├── components/ # Chat, panels, pages, auth, skill, MCP, team, file UI
│ │ ├── services/ # API clients and browser service integrations
│ │ ├── stores/ # Frontend state stores
│ │ ├── i18n/ # Locale files and tests
│ │ └── workers/ # Browser/PWA workers
│ ├── android/ # Capacitor Android project
│ ├── ios/ # Capacitor iOS project
│ ├── src-tauri/ # Tauri desktop shell
│ └── scripts/ # Frontend build, packaging, and i18n scripts
├── docs/ # VitePress documentation
├── deploy/ # Docker Compose deployment
├── k8s/ # Kubernetes manifests
├── nginx/ # Reverse proxy config
├── scripts/ # Sandbox and maintenance utilities
└── tests/ # Backend, API, infra, agent, and unit tests
Note — The project name "LambChat" and its logo may not be changed or removed.
Built for people who want AI agents that can actually do the work.
 Repository |
 Contact |
 Documentation |
 中文 README |
💬 WeChat for deployment help, product feedback, and collaboration
Powered by LINUX DO — A New Ideal Community