> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openreward.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Using Harbor Environments

> Convert Harbor tasks into OpenReward environments using harbor2or

## Goals

* Understand what [Harbor](https://harborframework.com) is and how its tasks map to OpenReward environments.
* Install and use the `harbor2or` CLI tool.
* Convert a Harbor task source into a deployable [ORS](https://openrewardstandard.io) environment.
* Build, test, and deploy the generated environment to OpenReward.

## Prerequisites

* An OpenReward [account](https://openreward.ai/) and [API key](https://openreward.ai/keys)
* Python 3.11+
* Docker installed locally (for building task images)
* Familiarity with [environments](/concepts/environments) and [deployment](/deployment/github-integration)

## What is Harbor?

[Harbor](https://harborframework.com) is a framework for defining agent tasks using a standardized directory structure. Each Harbor task includes instructions, a container environment (Dockerfile or pre-built image), verification tests, and optional oracle solutions.

The `harbor2or` CLI tool converts Harbor task repositories into [ORS](https://openrewardstandard.io) environments that can be deployed on OpenReward. It handles downloading tasks, generating environment server code, building Docker images, and validating tasks with oracle agents.

## Installation

Install `harbor2or` from GitHub:

```bash theme={null}
pip install git+https://github.com/OpenRewardAI/harbor2or.git
```

If you plan to use HuggingFace datasets as a source, install the optional dependencies:

```bash theme={null}
pip install huggingface_hub pyarrow
```

## Quick Start

<Steps>
  <Step title="Create the environment">
    Point `harbor2or create` at a Harbor task source. This can be a GitHub repository, a HuggingFace dataset, or a local directory:

    ```bash theme={null}
    harbor2or create <source> <name>
    ```

    For example, to convert Terminal-Bench into an OpenReward environment:

    ```bash theme={null}
    # From GitHub
    harbor2or create https://github.com/laude-institute/terminal-bench-2 terminal-bench

    # Or from HuggingFace
    harbor2or create zai-org/terminal-bench-2-verified terminal-bench
    ```

    This generates a complete [ORS](https://openrewardstandard.io) environment in `./terminal-bench/` containing:

    * `server.py` -- the environment server with tools and task logic
    * `Dockerfile` and `requirements.txt` -- for containerised deployment
    * `splits.json` and `tasks.txt` -- task metadata and split mappings

    You can customise the output with flags:

    ```bash theme={null}
    harbor2or create <source> <name> \
      --output ./custom-dir \
      --image-prefix myorg/env-name \
      --environment MyOrg/MyEnvironment
    ```
  </Step>

  <Step title="Build Docker images">
    Build the Docker images for each task locally:

    ```bash theme={null}
    harbor2or build terminal-bench --local
    ```

    This builds and pushes an image per task, then caches the image digest in each task's `sha.txt` file.

    <Info>
      For production workloads, `harbor2or build` also supports Google Cloud Build for parallel, remote image building. See the [harbor2or README](https://github.com/OpenRewardAI/harbor2or) for details.
    </Info>
  </Step>

  <Step title="Test with the oracle agent">
    Run the oracle agent on tasks that include a `solution/solve.sh` file:

    ```bash theme={null}
    export OPENREWARD_API_KEY='your-api-key'
    harbor2or test terminal-bench --concurrency 4 --verbose
    ```

    This starts a sandbox for each task, uploads and runs the oracle solution, then reports pass/fail results with a summary.
  </Step>

  <Step title="Deploy to OpenReward">
    Push the generated environment to GitHub and connect it via the OpenReward dashboard:

    ```bash theme={null}
    cd terminal-bench
    git init && git add -A && git commit -m "Initial environment"
    git remote add origin https://github.com/yourorg/terminal-bench.git
    git push -u origin main
    ```

    Then follow the [GitHub deployment guide](/deployment/github-integration) to connect the repository and trigger your first build on OpenReward.
  </Step>
</Steps>

## Tools

Harbor environments include the [ClaudeCodeToolset](/harnesses/harness-toolsets#claudecodetoolset) at the class level, which provides `bash`, `glob`, `grep`, `read`, `write`, `edit`, and `todo_write`. The environment also exposes a `submit_answer` tool for running verification and returning the reward.

<Info>
  When an agent calls `submit_answer`, the environment executes the `tests/test.sh` script from the original Harbor task to verify the result. The reward is read from `/logs/verifier/reward.txt` in the sandbox.
</Info>

## Supported Sources

The `harbor2or create` command accepts several source formats:

* **GitHub repository**: `https://github.com/org/repo`
* **HuggingFace dataset URL**: `https://huggingface.co/datasets/org/name`
* **HuggingFace short ID**: `org/name`
* **Local directory**: `./path/to/tasks`

Harbor tasks are auto-detected within the source. Each valid task must contain an `instruction.md`, `task.toml`, `tests/test.sh`, and either an `environment/Dockerfile` or a `docker_image` reference in `task.toml`.

## Next Steps

<CardGroup cols={3}>
  <Card title="harbor2or Reference" icon="github" href="https://github.com/OpenRewardAI/harbor2or">
    Full CLI reference, advanced options, and Cloud Build setup.
  </Card>

  <Card title="Your First Environment" icon="earth" href="/environments/your-first-environment">
    Learn the fundamentals of building ORS environments from scratch.
  </Card>

  <Card title="GitHub Deployment" icon="rocket" href="/deployment/github-integration">
    Connect your environment repository to OpenReward for automatic deployment.
  </Card>
</CardGroup>