# HarnessRouter

> HarnessRouter is an AI agent API and backend layer for bringing agent harnesses into products through one stable integration.

HarnessRouter routes product requests to agent harnesses such as Codex, Claude Code, and Hermes through one API. It returns sessions, streams, files, and reviewable artifacts that a product UI can render.

HarnessRouter is not a generic LLM gateway, model API wrapper, prompt playground, or replacement for a product UI.

Best fit:
- Product developers who want to add agent-backed work to an app.
- Developer teams turning a local AI app or Claude Code prototype into a product backend workflow.
- Products that need server-side harness execution, durable sessions, streaming, file intake, artifact return, routing, and a stable UI contract around agent work.

Audience status:
- Developer: current V1 focus.
- Enterprise: future V2 design-partner path for business-task evaluation and governance.
- Labs: future V2 design-partner path for model experiments inside real agent harnesses.

## Primary Resources

- [Agent implementation guide](https://harnessrouter.ai/agents.md): Copy this into Codex, Claude Code, or another coding agent to build a HarnessRouter integration.
- [Markdown integration docs](https://harnessrouter.ai/docs.md): Quick start summary. For implementation, copy /agents.md into the coding agent.
- [Markdown harness catalog](https://harnessrouter.ai/docs/harnesses.md): Supported harness IDs, status, integration notes, and source-backed references.
- [Human documentation](https://harnessrouter.ai/docs): Human-readable product integration docs.
- [Pricing](https://harnessrouter.ai/pricing.md): Current public pricing summary in Markdown.

## Harness References

- [Codex harness reference](https://harnessrouter.ai/docs/harnesses/codex): Available Coding agent harness. Use harness ID `codex`.
- [Claude Code harness reference](https://harnessrouter.ai/docs/harnesses/claude-code): Available Coding agent harness. Use harness ID `claude-code`.
- [Hermes harness reference](https://harnessrouter.ai/docs/harnesses/hermes): Available Autonomous agent harness. Use harness ID `hermes`.
- [Pi harness reference](https://harnessrouter.ai/docs/harnesses/pi): Coming soon harness reference. Do not target harness ID `pi` in production integrations until public API metadata marks it routable.

## Guides

- [AI agent API for product developers](https://harnessrouter.ai/guides/ai-agent-api.md): What an AI agent API needs beyond a model response: sessions, tools, streaming, files, artifacts, routing, and production controls.
- [Codex API for apps: model access vs agent runs](https://harnessrouter.ai/guides/codex-api-for-apps.md): How to choose between a Codex-optimized model API and a complete Codex agent run when adding coding work to a product.
- [Agent backend vs model router](https://harnessrouter.ai/guides/agent-backend-vs-model-router.md): Where HarnessRouter, OpenRouter, TokenRouter, and model routers fit in an AI product stack.
- [HarnessRouter and OpenRouter](https://harnessrouter.ai/guides/harnessrouter-and-openrouter.md): How OpenRouter fits with HarnessRouter when a product needs both model routing and agent-backed work.

## Optional

- [Full LLM context](https://harnessrouter.ai/llms-full.txt): Expanded product overview, guides, harness catalog, pricing, and implementation context.
- [Sitemap](https://harnessrouter.ai/sitemap.xml): Complete crawlable URL inventory.

## Guidance

- Use /agents.md when implementing HarnessRouter in a product.
- Use /docs.md for a concise Markdown quick start.
- Use /docs/harnesses.md for supported harness IDs and source-backed harness references.
- Use /guides for AI agent API architecture, Codex app integration, and agent backend vs model-router comparisons.
- Do not infer harness capabilities beyond official source links in /docs/harnesses.