---
title: "Harbor"
description: "[Harbor](https://github.com/laude-institute/harbor) is a framework from the creators of Terminal-Bench for evaluating and optimizing agents and language models. It uses LiteLLM to call 100+ LLM providers."
type: skill
canonical_url: https://claudary.paisolsolutions.com/skills/harbor
source: "Claudary"
difficulty: intermediate
author: "Claude Code Knowledge Pack"
date: 2026-07-10T11:24:01.021Z
license: CC-BY-4.0
attribution: "Harbor — Claudary (https://claudary.paisolsolutions.com/skills/harbor)"
---

# Harbor
[Harbor](https://github.com/laude-institute/harbor) is a framework from the creators of Terminal-Bench for evaluating and optimizing agents and language models. It uses LiteLLM to call 100+ LLM providers.

## Overview

# Harbor

[Harbor](https://github.com/laude-institute/harbor) is a framework from the creators of Terminal-Bench for evaluating and optimizing agents and language models. It uses LiteLLM to call 100+ LLM providers.

```bash
# Install
uv add harbor

# Run a benchmark with any LiteLLM-supported model
harbor run --dataset terminal-bench@2.0 \\
   --agent claude-code \\
   --model anthropic/claude-opus-4-1 \\
   --n-concurrent 4
```

Key features:
- Evaluate agents like Claude Code, OpenHands, Codex CLI
- Build and share benchmarks and environments
- Run experiments in parallel across cloud providers (Daytona, Modal)
- Generate rollouts for RL optimization

- [GitHub](https://github.com/laude-institute/harbor)
- [Documentation](https://harborframework.com/docs)

---

Source: [Claudary](https://claudary.paisolsolutions.com/skills/harbor) · https://claudary.paisolsolutions.com