harnessrouter

HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.

⭐ 3,730 stars on GitHub · 🍴 400 forks · 📜 License: apache-2.0 · 💻 Language: Python

What is harnessrouter?

An open-source AI/LLM project — run models locally, no cloud data sharing, fully customizable to your needs.

The biggest strength is fully local AI inference — zero API cost, no data leak risk, low latency.

Best for AI devs, researchers, anyone building agents/chatbots without OpenAI dependency.

Topics: the project is tagged with popular topics:

• 🏷️ agent-api
• 🏷️ agent-framework
• 🏷️ agent-harness
• 🏷️ ai-agents
• 🏷️ ai-infrastructure
• 🏷️ coding-agent
• 🏷️ conformance-testing
• 🏷️ deepseek-harness
• 🏷️ harness-engineering
• 🏷️ hermes

📸 Screenshots

Quick install

The project supports Docker Compose:

git clone https://github.com/HarnessRouter/harnessrouter.git
cd harnessrouter
docker compose up -d

Check the README in the repo for required env variables.

Minimum system requirements

⚡ Deploy fast on VSIS

Use the VSIS VPS Lite 2GB RAM / 2 vCPU / 25GB SSD (~104k/tháng) plan from VSIS.NET — high-speed VN-based VPS, 24/7 support, ideal for running harnessrouter 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: HarnessRouter/harnessrouter
• 🌐 Homepage: https://harnessrouter.ai/
• 📚 Official docs: see README in the repo
• 💬 Community: GitHub Issues + Discussions

Article compiled from GitHub data on 27/10/2026. Star/fork counts may have changed — see live numbers via the GitHub link.