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
This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.
100
review score
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.
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.
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.
Analysis
ReadyOriginal problem, capability, and verdict guidance are available.
Sources
ReadyRepository metadata and README/source references are attached.
License
ReadyApache-2.0 is recorded for review.
Maintenance
ReadyRecent activity is visible in repository metadata.
Alternatives
ReadyEnough nearby projects exist for comparison.
Momentum
3.7k Stars
Reuse
1.4k Forks
Attention
3.7k Watchers
Maintenance
active
License
Apache-2.0
Open issues
603
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
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
LLM Tool
Libraries and tools for LLM apps, RAG, prompts, and evals
pip install harbor73
Health Score
Active
Commit Activity
Aug 4, 2025
Created
Jul 31, 2026
Last push
+31
Today's growth
+31
7-day growth
+31
30-day growth
Forks
Open
Watchers
harbor-framework
GitHub profileobra/superpowers
An agentic skills framework & software development methodology that works.
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.
NousResearch/hermes-agent
The agent that grows with you
mattpocock/skills
Skills for Real Engineers. Straight from my .agents directory.
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.
✓
License
✓
Forked
✓ Active
Maintained
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.