open-multi-agent

TypeScript multi-agent framework that runs in your own environment: consequential actions wait for approval and every run leaves a verifiable record. Describe the goal, not the graph. 13 built-in providers (Claude, OpenAI, Gemini, DeepSeek and more) plus any OpenAI-compatible endpoint, local models included.

⭐ 6,903 stars on GitHub · 🍴 2,431 forks · 📜 License: mit · 💻 Language: TypeScript

What is open-multi-agent?

Building AI workflows usually means hardcoding brittle task graphs that break when edge cases arise. Instead of wiring up static nodes, you can define a high-level goal and let a dynamic orchestration layer compile the agent DAG at runtime

Topics: the project is tagged with popular topics:

• 🏷️ agent-framework
• 🏷️ agent-orchestration
• 🏷️ agentic-ai
• 🏷️ ai-agents
• 🏷️ ai-governance
• 🏷️ anthropic
• 🏷️ claude
• 🏷️ claude-code
• 🏷️ deepseek
• 🏷️ gemini

📸 Screenshots

Quick install

See the README for detailed install instructions. Most projects support Docker — if the repo has a Dockerfile, use:

git clone https://github.com/open-multi-agent/open-multi-agent.git
cd open-multi-agent
docker build -t open-multi-agent .
docker run -d -p 8080:8080 open-multi-agent

Minimum system requirements

⚡ Deploy fast on VSIS

Use the VSIS VPS Mini 1GB RAM / 1 vCPU / 15GB SSD (~70k/tháng) plan from VSIS.NET — high-speed VN-based VPS, 24/7 support, ideal for running open-multi-agent smoothly.

🎯 Benefits:

• One-command docker compose up -d deploy in 2 minutes
• Dedicated IPv4, root access, unmetered domestic bandwidth
• Daily snapshot backup
• Free install assistance from the VSIS team

👉 See matching VPS plans at vsis.net

Resources

• 🔗 GitHub: open-multi-agent/open-multi-agent
• 🌐 Homepage: https://open-multi-agent.com/go/repo
• 📚 Official docs: see README in the repo
• 💬 Community: GitHub Issues + Discussions

Article compiled from GitHub data on 10/09/2026. Star/fork counts may have changed — see live numbers via the GitHub link.