HarnessRouter/harnessrouter

Build agent products without handling harness engineering. HarnessRouter is the infrastructure layer that turns existing harnesses like Codex and Claude Code into plug-and-play agent backends, letting your product run tasks, retrieve results, and switch harnesses through one API.

HarnessRouter implements the Unified Harness Protocol (UHP) and provides an OpenAI Responses-compatible API, handling persistent sessions, streaming progress, files, artifacts, cancellation, and structured failures.

Eight harness × model configurations on the same task. Each metric compares its best and worst results. The lowest-cost and fastest configurations vary by task. Methodology

Self-host Community Edition with your own provider keys, on infrastructure you control.

Start with one Docker command, wait for the first launch, then connect a model provider and run your first task.

You need: Docker · About 4 GB of disk · A provider API key

No HarnessRouter account required. No bundled model or trial key.

docker run -d --name harnessrouter \
  -p 127.0.0.1:3000:3000 \
  -v harnessrouter:/data \
  harnessrouter/harnessrouter

Docker pulls the image if needed. The named volume preserves your database, files, installed harness CLIs, and workspaces between restarts.

docker logs -f harnessrouter

The first launch installs the enabled harness CLIs. Continue when the logs show:

[harnessrouter] ready on :3000

Press Ctrl+C to stop following logs. The container keeps running.

Open http://localhost:3000, or your chosen host port, and sign in:

Using an existing volume or custom credentials? Check credential precedence and setup.

These credentials sign you into the Console. You do not need a HarnessRouter API key to run tasks here.

Open Bring Your Own Key in the sidebar and press Add Integration. Choose a provider, give the integration a name, and add its API key. Its supported models become available in the Console.

This provider key authorizes model requests. It is separate from the HarnessRouter API key used for product integration below.

Open Agent harnesses, choose a supported harness, and select New task. Pick an available model and give the agent a concrete task. Follow live progress and open the files it produces in the same session.

_{In the illustrative run above, Hermes reviews a fictional NDA and produces a redlined version, a clean copy, and a negotiation memo.}

Built-in harnesses work without this step. Create a custom harness when you want reusable behavior tailored to your product.

1. Create. Select New harness in Agent harnesses. In Add harness, set the Name, Base harness, and Default model together, then select Create and configure.
2. Customize. In Harness Settings, add Agent instructions, configure Tools (use Add MCP for an optional MCP server), and add Skills as needed.
3. Save and test. Select Save Changes, then Run Task to test the saved configuration.

You can change the default model later in Settings, but the base harness cannot be changed after creation.

Run product tasks with built-in or custom harnesses as pluggable agent backends. Call your self-hosted instance’s OpenAI Responses-compatible API and select the harness with metadata.harness_id. No Cloud deployment is required.

Once your harness runs successfully in the Console:

1. Open API Keys in the Console sidebar of the same CE instance (default local address) and choose Create API key.
2. Store the secret shown once as HARNESSROUTER_API_KEY in your product backend. Never expose it in browser code. This CE-issued key is separate from your Console password and provider key.
3. Call the API with the Harness ID shown in the Console and a model served by your connected provider.

export HARNESSROUTER_BASE_URL=http://localhost:3000/api/harness

curl --fail-with-body -sS "$HARNESSROUTER_BASE_URL/v1/responses" \
  -H "Authorization: Bearer ${HARNESSROUTER_API_KEY:?}" \
  -H 'content-type: application/json' \
  -d '{
    "input":"Reply with exactly: it works.",
    "metadata":{"harness_id":"codex"},
    "model":"gpt-5.4-mini",
    "stream":false
  }'

The task and its transcript appear in the same workspace in the Console. Set "stream": true to receive server-sent events.

Never put a long exact value such as a token, an id or a hash in the prompt: the agent retypes what it reads, and a model drops and swaps characters in strings like that. Attach it as a file (POST /v1/files, then an input_file block; the file lands in the agent's working directory under its filename before every turn that carries it) or hand it to the agent through the harness's environment. A harness takes an env map whose values resolve on every turn: $headers.X-Name takes that header from the request (declare it in additional_headers), vault:name takes a stored secret, anything else is used as written. The agent's shell and tools start with those variables set, so a task can say "the token is in $DEPLOY_TOKEN", and a value that came through a reference is redacted from everything that leaves the sandbox, the response, the stream, the trace and the stored record, even when the agent prints it. A vault: reference reads only a secret your own workspace stored through PUT /v1/mcp-secrets/{ref}. The redaction protects the record, not the agent: a value the agent can read it can also send elsewhere if a prompt or a page tells it to, so hand it a token scoped to the user and the task, short-lived and least privilege.

The whole API is described at $HARNESSROUTER_BASE_URL/v1/openapi.json, generated from the routes, with a browsable copy at /v1/docs.

The default URL works when your backend and CE run on the same computer. From another machine or container, use a reachable URL for the CE instance. Read the complete self-hosted API and networking guide →

Power agentic features in your product with agent harnesses, including knowledge-work tasks such as creating content and analyzing data. Explore these ready-to-use kits to see harnesses in action as pluggable backends.

Slides An agent harness turns your brief into slide content and layouts for an editable deck.	Sheets An agent harness uses each row’s data to execute a task and writes the result back into the sheet.
Dashboards An agent harness reads your database schema and writes SQL queries to power dashboard charts.	Videos An agent harness turns your brief into a shot plan and calls video tools to generate clips for the timeline.
My Workplace A recruiter harness interviews you and installs each teammate as a harness of its own; teammates work together in groups, hand each other files and @mentions, and leave what they make in a shared library.

Explore the Starter Kits →

• Your infrastructure. One Docker deployment for the Console, Gateway, and Runner.
• Your credentials and state. Provider keys, sessions, files, and workspaces stay under your control. Model requests still go to your configured provider.
• Real workspaces. Native filesystem, shell, and Git workflows, with separate session workspaces.
• No Console product analytics. Community Edition disables the Console analytics pipeline.

Choose HarnessRouter Cloud for managed deployment, maintenance, and scaling, with tasks running in serverless, isolated sandboxes through the same API contract.

For local uploads: set HR_SECRET_KEY on your local instance to encrypt the saved destination key. Save your custom harness in Settings, select Upload to Cloud, then connect a destination using its Cloud workspace API key.

Uploads copy harness configuration, not provider keys, sessions, or generated files. Uploading again replaces that destination’s hosted copy.

┌─ HarnessRouter container ─────────────────────────────────┐
│  Console :3000   ← only published port                    │
│       │ same-origin proxy                                 │
│       ▼                                                   │
│  Gateway :8080   Responses API + harness lifecycle        │
│       │ loopback                                          │
│       ▼                                                   │
│  Runner  :8081   runs harnesses in session workspaces     │
│                                                           │
│  /data volume   database · files · secrets · workspaces   │
└───────────────────────────────────────────────────────────┘

The Gateway and Runner listen on loopback inside the container. Sessions use separate workspaces and operating-system users, not separate containers. The Console is the entry point for both UI and API.

See configuration, upgrades and backups, and public deployment with TLS.

Unified Harness Protocol (UHP) is the public, versioned contract implemented by Community Edition and HarnessRouter Cloud. Its task surface is deliberately compatible with the OpenAI Responses API, so existing Responses SDKs, streaming parsers, and UI components can work with a UHP server. UHP defines harness execution semantics for harness selection, persistent sessions, files, cancellation, and harness-managed tools and skills.

This repository contains the Apache 2.0 reference implementation, machine-readable schemas, and the conformance suite.

HarnessRouter Community Edition is licensed under Apache 2.0. Agent harness CLIs are installed on first launch and remain subject to their respective upstream licenses. See NOTICE for third-party notices and the Starter Kits repository for its separate licensing terms.

HarnessRouter is the world's first unified interface for agent harnesses.