lobehub/lobehub

👋🏻 Getting Started & Join Our Community

We are a group of e/acc design-engineers, hoping to provide modern design components and tools for AIGC.

Whether for users or professional developers, LobeHub will be your AI Agent playground. Please be aware that LobeHub is currently under active development, and feedback is welcome for any issues encountered.

[!IMPORTANT]

Star Us, You will receive all release notifications from GitHub without any delay ~ ⭐️

✨ Features

Day 1 Welcome to the team

You add it to your team chat and ask it to read up. By lunch it has gone through the history and said hello to everyone.

Week 1 Its first task

Someone posts a feature request in Discord and nobody assigns it. Lobe AI takes it on, and you only step in once, to accept the result.

Month 1–2 Settling in as the team grows

Everyone now has their own agent, and design, releases and docs each have a dedicated one. Lobe AI is still learning when to speak up and when to stay quiet.

Month 3 It passes its review

When it started, it got about half of these right. Now it rarely misses, and every correction you gave it has become a lesson it keeps.

🧩 Marketplace

Find agents, MCP servers and skills on lobehub.com, add them to your workspace, or publish your own.

Publish your own

• Agents: submit one from its settings in LobeHub. The Creator Reward Program features a community agent every two weeks.

• MCP servers: ask your agent to Read https://lobehub.com/publish-mcp/skill.md and follow the instructions to publish my MCP server to the LobeHub Marketplace, or use the CLI:

  npx -y @lobehub/market-cli login
  npx -y @lobehub/market-cli plugin submit https://github.com/OWNER/REPOSITORY
  

• Skills: submit a GitHub repository from the Skills marketplace.

📖 Documentation

All documentation lives at lobehub.com/docs:

🛳 Self Hosting

Run LobeHub on your own infrastructure and keep your data with you. The full guide is in 📘 Build your own LobeHub.

A Docker Compose (recommended)

Starts LobeHub with PostgreSQL, Redis, RustFS file storage, SearXNG search and the agent gateway. Runs on Linux and macOS, or on Windows through WSL 2.

mkdir lobehub && cd lobehub
bash <(curl -fsSL https://lobe.li/setup.sh) -l en
docker compose up -d

Then open . Ports, LAN and domain modes, and upgrades are covered in the 📘 Docker Compose guide.

B One-click deploy

Vercel needs a PostgreSQL database, S3-compatible storage and a few secrets before you deploy. The 📘 Vercel guide walks through each one.

⌨️ Local Development

You can use GitHub Codespaces for online development:

Or clone it for local development:

$ git clone https://github.com/lobehub/lobehub.git
$ cd lobehub
$ pnpm install
$ bun run dev       # Full-stack (Next.js + Vite SPA)
$ bun run dev:spa   # SPA frontend only (port 9876)

Debug Proxy: After running dev:spa, the terminal prints a proxy URL like https://app.lobehub.com/_dangerous_local_dev_proxy?debug-host=http%3A%2F%2Flocalhost%3A9876. Open it to develop locally against the production backend with HMR — a development convenience, not a place to verify a change.

If you would like to learn more details, please feel free to look at our 📘 Development Guide.

🤝 Contributing

Contributions of all types are more than welcome; if you are interested in contributing code, feel free to check out our GitHub Issues and Projects to get stuck in to show us what you’re made of.

[!TIP]

We are creating a technology-driven forum, fostering knowledge interaction and the exchange of ideas that may culminate in mutual inspiration and collaborative innovation.

Help us make LobeHub better. Welcome to provide product design feedback, user experience discussions directly to us.

Principal Maintainers: @arvinxx @canisminor1990

❤️ Sponsor

Every bit counts and your one-time donation sparkles in our galaxy of support! You’re a shooting star, making a swift and bright impact on our journey. Thank you for believing in us – your generosity guides us toward our mission, one brilliant flash at a time.

🔬 Research

• 📊 MCPMark: A stress-testing benchmark for MCP. Its tasks are realistic, multi-step and verifiable, covering file systems, databases, Playwright browser automation, GitHub and more. Built by EVAL SYS, LobeHub and the National University of Singapore, and open source under Apache-2.0.
• 📄 Research paper: Read our research paper on Hugging Face Papers.
• 🧪 EVAL SYS: An evaluation systems organization, one of the teams behind MCPMark.

---

Copyright © 2026 LobeHub. This project is LobeHub Community License licensed.