HarnessRouter
DocsSign up

Backed by Y Combinator

Bring the world's best AI agents into your app, with one API.

Codex, Claude Code, Hermes, and more. Ready to run as your product backend.

Get API keyRead docs

Launch Partner:

Used by

The problem

Building AI agent backend for takes months.

Your backlog, if you build it yourself.
  • sandbox per run
  • agent runtime
  • tool orchestration
  • files & artifacts
  • sessions & streaming
  • retries & timeouts
  • permissions
  • cost controls

And the upgrades, fixes, and maintenance never stop.

The solution

We run the AI agent backend. You ship it in minutes.

One API brings leading AI agents into your app.
  • Codex
  • Claude Code
  • Hermes

We take care of the upgrades, fixes, and maintenance for you.

The steps

Build it in three steps.

codex · claude code
1 · drop it into your coding agent
“Build a founder launch-video app: users drop a logo and an idea, get a launch video.”
2 · describe your idea
server envHR_KEY=sk-hr-••••••••
3 · add your API key securely
SHIP
Get API key

Use cases

Some AI features your app can ship, and more.

Your appSite builder
HarnessRouterOne API
  • CodexCode, apps and images
  • Claude CodeCode, files and documents
  • HermesAutonomous, any frontier model
  • PiSoonCoding agent
    Soon

Every harness ready, one API

Control

Your AI agents, under control.

Trace every task, step by step. Configure each harness when you need to.

HarnessRouter

Selected Harness

Cinematic Product Launch Video Generator

HealthyCodexgpt-5.593 events11m 24s
Execution overview
0:005:4211:24

Event timeline

UserCreate a premium MP4 launch video for this AI product.
TooluserMessage
AgentI’ll generate the launch video directly in the workspace.
ToolcommandExecution pwd && rg --files
AgentI’ve got the rendering path now.
ToolfileChange /workspace/render_launch_video.py
AgentThe final encode passed inspection.
Resultlaunch-video.mp4

Launch video

See it in action.

Q&A

The question everyone asks first.

What exactly is a harness?

A harness is the execution layer around a model: instructions, model policy, tools and MCP, skills, runtime and sandbox, permissions and guardrails, plus the output contract. It is what lets a model do work and return artifacts instead of only replying with text.

Why not just use Codex or Claude directly?

You should use them to build your app. HarnessRouter solves a different problem: it brings the capabilities of Codex and Claude Code into your product. Your users get finished work without opening a terminal or leaving your product. With HarnessRouter, your app can run AI agents that create real artifacts for your users: videos, games, codebases, docs, and more, through one API.

How much does it cost?

Start with a 7-day trial. After that, choose a monthly platform plan: Developer, Production, or Scale. Plans include credits for production agent work; additional usage runs from top-up balance with budgets and hard caps.

Do I need to understand agents to use this?

No. Drop our AGENTS.md into Cursor or Claude Code, describe your feature, and your coding agent wires everything: the endpoint, the config, the UI. The demos above were built exactly this way.

Am I locked into one harness?

The opposite. That is the point. Your config names the harness: claude-code today, codex tomorrow, or back again, swapped anytime with one line. Your integration code and output schema never change. When a better harness ships next quarter, your product gets better with a config change.

What exactly comes back to my app?

Structured, renderable results: code changes as reviewable diffs, generated files and documents, images, and confirmations of real tool actions like GitHub, Slack, Notion, or internal APIs. Your UI decides how to show them and when the user accepts.