{"name":"HarnessRouter: Unified Interface for AI Agent Harnesses","description":"HarnessRouter Community Edition provides a self-hosted, Apache-2.0 licensed unified interface for various AI agent harnesses like Codex, Claude Code, and Hermes. It allows users to run multiple agents through a single API, offering features such as sessions, streaming, file handling, and cancellation. The project implements the open-standard Unified Harness Protocol (UHP), ensuring users maintain control over their keys and infrastructure.","github":"https://github.com/HarnessRouter/harnessrouter","url":"https://osrepos.com/repo/harnessrouter-harnessrouter","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/harnessrouter-harnessrouter","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/harnessrouter-harnessrouter.md","json":"https://osrepos.com/repo/harnessrouter-harnessrouter.json","topics":["AI Agents","Agent Framework","LLM","Open Source","Self-Hosted","Unified API","Python","AI Infrastructure"],"keywords":["AI Agents","Agent Framework","LLM","Open Source","Self-Hosted","Unified API","Python","AI Infrastructure"],"stars":null,"summary":"HarnessRouter Community Edition provides a self-hosted, Apache-2.0 licensed unified interface for various AI agent harnesses like Codex, Claude Code, and Hermes. It allows users to run multiple agents through a single API, offering features such as sessions, streaming, file handling, and cancellation. The project implements the open-standard Unified Harness Protocol (UHP), ensuring users maintain control over their keys and infrastructure.","content":"## Introduction\n\nHarnessRouter Community Edition is an open-source, self-hosted platform that provides a unified interface for various AI agent harnesses. It allows developers to integrate and manage different agent backends, such as Codex, Claude Code, Hermes, and DeepSeek Harness, through a single, consistent API. By implementing the open-standard Unified Harness Protocol (UHP), HarnessRouter simplifies the development of agent products, abstracting away complex harness engineering.\n\n## Why Use It and Benefits\n\nHarnessRouter offers significant advantages for building agent-powered applications. It eliminates the need to handle individual harness integrations, allowing products to switch between different agent backends to optimize for cost and latency. Users benefit from full control over their infrastructure, credentials, and state, as provider keys, sessions, files, and workspaces remain self-hosted. The platform provides real workspaces, native filesystem, shell, and Git workflows, ensuring robust and secure agent operations without Console product analytics.\n\n## Installation\n\nTo get started with HarnessRouter Community Edition, you need Docker and a provider API key.\n\n1.  **Start HarnessRouter:**\n    bash\n    docker run -d --name harnessrouter \\\n      -p 127.0.0.1:3000:3000 \\\n      -v harnessrouter:/data \\\n      harnessrouter/harnessrouter\n    \n    This command pulls the Docker image and starts the container, preserving your data across restarts with a named volume.\n\n2.  **Wait for the first launch:**\n    Monitor the logs until you see `[harnessrouter] ready on :3000`.\n    bash\n    docker logs -f harnessrouter\n    \n\n3.  **Open the console:**\n    Access the web console at [http://localhost:3000](http://localhost:3000) and sign in with the default username `harnessrouter` and password `harnessrouter`. Remember to change the default password immediately for security.\n\n4.  **Connect a model provider:**\n    In the console, go to \"Bring Your Own Key\", add an integration, choose a provider, and enter your API key. This makes its models available for tasks.\n\nFor detailed setup, including custom configurations and upgrades, refer to the official documentation.\n\n## Examples\n\nOnce HarnessRouter is set up and a model provider is connected, you can start running tasks.\n\n**Running a task in the Console:**\nNavigate to \"Agent harnesses\", select a supported harness, and choose \"New task\". Provide the agent with a concrete task, select an available model, and observe the live progress. You can also review files produced within the same session.\n\n**Integrating with your product backend via API:**\nHarnessRouter provides an OpenAI Responses-compatible API for seamless integration into your product.\n\n1.  **Create an API key:**\n    In the Console, go to \"API Keys\" and create a new API key. Store this secret securely as `HARNESSROUTER_API_KEY` in your backend.\n\n2.  **Call the API:**\n    Use `curl` or your preferred HTTP client to interact with the API, specifying the `harness_id` and `model`.\n    bash\n    export HARNESSROUTER_BASE_URL=http://localhost:3000/api/harness\n\n    curl --fail-with-body -sS \"$HARNESSROUTER_BASE_URL/v1/responses\" \\\n      -H \"Authorization: Bearer ${HARNESSROUTER_API_KEY:?}\" \\\n      -H 'content-type: application/json' \\\n      -d '{\n        \"input\":\"Reply with exactly: it works.\",\n        \"metadata\":{\"harness_id\":\"codex\"},\n        \"model\":\"gpt-5.4-mini\",\n        \"stream\":false\n      }'\n    \n    The full API documentation is available at `$HARNESSROUTER_BASE_URL/v1/openapi.json` and a browsable version at `/v1/docs`.\n\n## Links\n\n*   [Official GitHub Repository](https://github.com/HarnessRouter/harnessrouter)\n*   [HarnessRouter Cloud & Integration Docs](https://harnessrouter.ai/docs)\n*   [Unified Harness Protocol (UHP)](https://unifiedharnessprotocol.org)\n*   [Join the Community (Discord)](https://discord.gg/nPcbwqVPb2)\n*   [Starter Kits Repository](https://github.com/HarnessRouter/starter-kit)","metrics":{"detailViews":2,"githubClicks":0},"dates":{"published":null,"modified":"2026-09-22T16:55:16.000Z"}}