harbor-framework

    harbor-framework/harbor

    Framework for evaluating and improving agents

    backend
    evals
    rl-environments
    terminal-bench
    Python
    Apache-2.0
    6.5K stars
    2.1K forks
    6.5K GitHub watchers
    Updated Oct 26, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    5 releases in the last 90 days, the latest 1 day ago, with 359 contributors on GitHub.

    Gained 45% more stars in the last 90 days than in the 90 days before.

    Use Cases & Benefits

    • Provides a framework for evaluating and optimizing AI agents and language models across diverse benchmarks and environments.
    • Enables scalable, parallel experimentation and benchmarking with support for multiple agents, datasets, and cloud providers.
    • Use for benchmarking language models like Claude Code or Codex CLI on standardized datasets such as Terminal-Bench-2.0.
    • Use for conducting large-scale reinforcement learning experiments by generating rollouts in thousands of environments.
    • Use for building and sharing custom benchmarks and evaluation environments tailored to specific AI agent capabilities.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Apache 2.0

    Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.

    Community files

    • README: present
    • Contributing guide: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    About harbor

    Framework for evaluating and improving agents

    https://harborframework.com/

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Jul 31: +31Aug 1: +26Aug 2: +21Aug 3: +26Aug 4: +55Aug 5: +45Aug 6: +47Aug 7: +63Aug 8: +21Aug 9: +22Aug 10: +38Aug 11: +21

    +2,817 stars over 89 days across 18 snapshot days; best day +63 on Aug 7.

    Forks

    2.1K+651

    Open issues

    1.2K+568

    Compared with peers in Backend

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth

    harbor-framework/harbor compared with Backend repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    anthropics/skills187.8K+2.9K15—
    DuarteSantos8/openGym19.7K+2.4K602 days ago
    shiyu-coder/Kronos47.0K+2.3K16—
    NationalSecurityAgency/ghidra98.2K+2.3K6414 days ago
    microsoft/VibeVoice56.0K+1.1K29—
    harbor-framework/harbor6.5K—601 day ago
    Category median56.0K+2.3K29—

    Also by harbor-framework

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description