Privacy and advertising choices

Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy

LogoGit-Stars
Top StarsTrendingAI AgentsDaily PicksViral ReposInsights
LogoGit-Stars

Discover top GitHub projects with real rankings and AI insights

GitHub
Built withLogo of Git-StarsGit-Stars
Rankings
  • Top Stars
  • Trending
  • AI Agents
  • Daily Picks
  • Explore
Resources
  • Insights
  • Editorial Policy
About
  • About
  • Contact
Legal
  • Privacy Policy
  • Terms of Service
© 2026 Git-Stars. All Rights Reserved.
HA

harbor-framework/harbor

AI Agent

Framework for evaluating and improving agents

3.7k Stars1.4k Forks603 Open Issues3.7k WatchersPythonApache-2.0
AI AgentLLM Tool
Review Readiness

This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.

100

review score

Indexable review
Decision Snapshot

Problem solved

Harbor solves the fragmentation and reproducibility problem in agent evaluation by providing a unified harness that works with diverse agents (e.g., Claude Code, OpenHands) and benchmarks (e.g., Terminal-Bench, SWE-Bench), while supporting parallel execution and RL rollout generation.

Deployment reality

The available setup signal starts with: pip install harbor. Treat this as a starting point, then ask Codex or Claude to inspect the README, environment variables, runtime version, and deployment target before production use.

Commercial use

The recorded license is Apache-2.0. This is a useful commercial-use signal, but teams should still verify license text, dependencies, model/API terms, and trademark constraints.

Capability ceiling

Developers can evaluate any agent against existing benchmarks, create and share custom benchmarks, run thousands of parallel environments using providers like Daytona and Modal, and generate rollouts for reinforcement learning optimization. Real-world use cases include benchmarking coding agents, testing model improvements, and scaling agent evaluation for research.

Source and compliance noteLast synced: Aug 1, 2026

Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.

Original GitHub sourceMethodologyEditorial Policy
Editorial Evaluation

harbor-framework/harbor is tracked as a Python project in the AI Agent, LLM Tool area. This evaluation combines public GitHub metadata, category signals, short source summaries, and Git-Stars editorial rules rather than copying project documentation.

Momentum check: the repository has 3.7k total stars, with +0 today, +233 this week, and +0 this month. These growth windows help distinguish durable adoption from short-lived visibility spikes.

Maintenance check: current activity is Active; the latest push was 23 days ago, and the open issue queue is 603, about 16.21% of total stars. Treat this as an adoption signal, not a substitute for engineering due diligence.

Adoption check: 1.4k forks and 3.7k watchers suggest how often the project is reused or followed. License signal: Apache-2.0. Always verify license compatibility before commercial or internal use.

Practical fit: this project is most relevant when you need Python teams evaluating ecosystem-native tooling. Be cautious when you have low tolerance for large unresolved issue queues.

Source check: Git-Stars currently has 2 explicit source reference(s) for this report and a recent growth signal of 233. Follow the original GitHub repository for final install, security, and release information.

Evidence Checklist

Analysis

Ready

Original problem, capability, and verdict guidance are available.

Sources

Ready

Repository metadata and README/source references are attached.

License

Ready

Apache-2.0 is recorded for review.

Maintenance

Ready

Recent activity is visible in repository metadata.

Alternatives

Ready

Enough nearby projects exist for comparison.

Best For
  • Python teams evaluating ecosystem-native tooling
  • use cases where recent maintenance matters
Avoid When
  • you have low tolerance for large unresolved issue queues
  • you need a legal review, security audit, or production SLA
Adoption Signals

Momentum

3.7k Stars

Reuse

1.4k Forks

Attention

3.7k Watchers

Maintenance

active

License

Apache-2.0

Open issues

603

Overview

Harbor is a framework for evaluating and optimizing agents and language models, supporting arbitrary agents like Claude Code and OpenHands, and enabling parallel experiments across cloud providers.

Key Features

- Evaluate arbitrary agents (Claude Code, OpenHands, Codex CLI, etc.) - Build and share custom benchmarks and environments - Run experiments in thousands of parallel environments via providers like Daytona, Modal, and LangSmith

Tool Positioning

AI Agent

Agent frameworks, autonomous workflows, and tool-use systems

LLM Tool

Libraries and tools for LLM apps, RAG, prompts, and evals

Quick Start
pip install harbor
View on GitHub Project Homepage
Project Activity

73

Health Score

Active

Commit Activity

Aug 4, 2025

Created

Jul 31, 2026

Last push

Source Trail

GitHub repository metadata

metadata

GitHub README

readme_summary

Star History

+31

Today's growth

+31

7-day growth

+31

30-day growth

Jul 31, 2026Aug 1, 2026
Community Health
1.4k

Forks

603

Open

3.7k

Watchers

Owner
HA

harbor-framework

GitHub profile
Topics & Language
Pythonevalsrl-environmentsterminal-bench
Ecosystem & Usage
GitHub Repository Project Website
Alternatives & Comparison

obra/superpowers

An agentic skills framework & software development methodology that works.

273k

affaan-m/ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

240k

NousResearch/hermes-agent

The agent that grows with you

231k

mattpocock/skills

Skills for Real Engineers. Straight from my .agents directory.

218k

multica-ai/andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

203k
License
Apache-2.0
CreatedAug 4, 2025
Last pushJul 31, 2026
Last syncedAug 1, 2026
Repository Standards

✓

License

✓

Forked

✓ Active

Maintained

AI AnalysisAnalyzed by Git-Stars

Problem Solved

Harbor solves the fragmentation and reproducibility problem in agent evaluation by providing a unified harness that works with diverse agents (e.g., Claude Code, OpenHands) and benchmarks (e.g., Terminal-Bench, SWE-Bench), while supporting parallel execution and RL rollout generation.

Capabilities

Developers can evaluate any agent against existing benchmarks, create and share custom benchmarks, run thousands of parallel environments using providers like Daytona and Modal, and generate rollouts for reinforcement learning optimization. Real-world use cases include benchmarking coding agents, testing model improvements, and scaling agent evaluation for research.

Bottom Line

Harbor is ideal for researchers and engineers who need a scalable, reproducible way to evaluate and improve agents across multiple benchmarks and environments. It may be overkill for simple single-agent testing, but its parallel execution and provider integration make it powerful for serious evaluation workflows.

Full AI Analysis