Build agent products without handling harness engineering. HarnessRouter is the infrastructure layer that brings Codex, Claude Code, Hermes, DeepSeek Harness, and more into your product as agent backends 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
Tip
Get started: Run locally · Integrate into your product · Starter kits · Use managed Cloud
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/harnessrouterDocker pulls the image if needed. The named volume preserves your database, files, installed harness CLIs, and workspaces between restarts.
Existing installation or custom setup
Already installed? docker pull harnessrouter/harnessrouter downloads the latest image but does not upgrade a running container. Follow the upgrade and backup guide.
Port 3000 busy? Use -p 127.0.0.1:3100:3000 and open port 3100 instead. Keep the loopback binding while using the initial credentials.
Do not add --user. The entrypoint and Runner need root to manage per-session users. The Console and Gateway run unprivileged; agent processes run as their session’s user.
For version pinning, Compose, and scripted setup, see the setup guide.
docker logs -f harnessrouterThe 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.
Console not ready or a harness missing?
If the browser refuses the connection, retry after a few seconds while the Console finishes starting. For a missing harness, check backends available: and any requested but not installed warning in the logs.
Open http://localhost:3000, or your chosen host port, and sign in:
| Username | harnessrouter |
|---|---|
| Password | harnessrouter |
Warning
Change the default password in Profile. Keep the instance local until you change it. Saving briefly restarts the Console and signs out other browsers.
See the sign-in screen
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 Integrations → 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.
See the provider setup screen
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.
- Create. Select New harness in Agent harnesses. In Add harness, set the Name, Base harness, and Default model together, then select Create and configure.
- Customize. In Harness Settings, add Agent instructions, configure Tools (use Add MCP for an optional MCP server), and add Skills as needed.
- 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.
Watch the configuration walkthrough · 48 seconds
Configure DeepSeek Harness for customer-feedback analysis.
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:
- Open
/keyson the same CE instance (default local address) and choose Create API key. Open this URL directly if API keys is not visible in the sidebar. - Store the secret shown once as
HARNESSROUTER_API_KEYin your product backend. Never expose it in browser code. This CE-issued key is separate from your Console password and provider key. - 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.
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 →
| Your application can… | How |
|---|---|
| Start tasks | Send instructions and check execution status |
| Continue sessions | Send follow-up instructions with previous_response_id |
| Stream progress | Receive live updates as the agent works |
| Work with files | Attach input files and retrieve generated outputs |
| Cancel tasks | Stop work that is no longer needed |
| Inspect execution | Review structured errors and execution traces |
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.
An agent harness turns your brief into slide content and layouts for an editable deck. |
An agent harness uses each row’s data to execute a task and writes the result back into the sheet. |
An agent harness reads your database schema and writes SQL queries to power dashboard charts. |
An agent harness turns your brief into a shot plan and calls video tools to generate clips for the timeline. |
Setup notes & licensing
Start: Open Starter Kits in the Console and select a harness and model supported by your connected providers.
Dashboards: use a reachable database and a read-only database account. Set HR_SECRET_KEY to encrypt stored connections, and review the sample-row setting before connecting.
Licensing: Starter Kits use different terms from Community Edition.
- 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.
| Local → Cloud | Start directly in Cloud |
|---|---|
| Bring a custom harness you’ve configured locally. Follow the upload guide → |
Create and run harnesses without a local deployment. Open HarnessRouter Cloud → |
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.
| Resource | Purpose |
|---|---|
| Specification | Normative protocol behavior |
| OpenAI Responses compatibility | Compatibility with existing OpenAI Responses API clients |
| OpenAPI and JSON Schema | Machine-readable contracts |
| Conformance suite | Testable compatibility requirements |
| Governance | How the standard evolves |
| Goal | Resources |
|---|---|
| Build | Cloud & integration docs · API guide · Starter kits |
| Deploy | Setup & operations · Local → Cloud · HarnessRouter Cloud |
| Protocol | Unified Harness Protocol (UHP) |
| Community | Join the community (Discord) · Contribute · LinkedIn · X · Security |
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.