◐ Shell
clean mode source ↗

Harbor

  • harbor Public

    Harbor is a framework for running agent evaluations and creating and using RL environments.

    harbor-framework/harbor’s past year of commit activity

  • terminal-bench-science Public

    Terminal-Bench-Science: Evaluating AI Agents on Complex Real-World Scientific Workflows in the Terminal

    harbor-framework/terminal-bench-science’s past year of commit activity

    Python

    148

    Apache-2.0

    79 9 54

    Updated Jun 20, 2026

  • terminal-bench-3 Public

    Measuring agents' ability to get work done on a computer

    harbor-framework/terminal-bench-3’s past year of commit activity

  • harbor-framework/t-bench-docs’s past year of commit activity

    TypeScript

    8 14 2 1

    Updated Jun 18, 2026

  • harbor-framework/terminal-bench-challenges’s past year of commit activity

    Shell

    13 3 0 2

    Updated Jun 18, 2026

  • harbor-framework/harbor-adapters-experiments’s past year of commit activity

    Python

    7

    Apache-2.0

    12 0 0

    Updated Jun 16, 2026

  • harbor-framework/docs’s past year of commit activity

    MDX 0 MIT 0

    0 0

    Updated Jun 3, 2026

  • harbor-framework/benchmark-template’s past year of commit activity

    Python

    13 10 7 7

    Updated May 30, 2026

  • awesome-harbor Public

    A curated list of awesome Harbor ecosystem projects

    harbor-framework/awesome-harbor’s past year of commit activity

    42 2 0 1

    Updated May 29, 2026

  • harbor-framework/harbor-datasets’s past year of commit activity