Repositories list

• terminal-bench-science

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

  ai4scienceai-for-scienceagentic-ai

  ai4scienceai-for-scienceagentic-ai

  Python

  •

  Apache License 2.0

  •32•50•1•12•Updated Apr 4, 2026Apr 4, 2026

• harbor

  Public

  harbor-framework/harbor’s past year of commit activity
  Harbor is a framework for running agent evaluations and creating and using RL environments.

  rl-environmentsevalsterminal-bench

  rl-environmentsevalsterminal-bench

  Python

  •

  Apache License 2.0

  •868•1.3k•87•186•Updated Apr 4, 2026Apr 4, 2026

• t-bench-docs

  Public
  TypeScript

  •13•6•2•0•Updated Apr 3, 2026Apr 3, 2026

• terminal-bench-3

  Public
  🚧 Accepting Task Submissions 🚧

  Python

  •110•108•0•71•Updated Apr 3, 2026Apr 3, 2026

• benchmark-template

  Public template
  Harbor Benchmark Template

  Python

  •7•7•7•6•Updated Apr 3, 2026Apr 3, 2026

• terminal-bench-2

  Public
  Shell

  •

  Apache License 2.0

  •57•153•10•17•Updated Apr 1, 2026Apr 1, 2026

• harbor-docs

  Public
  MDX

  •9•2•0•6•Updated Mar 31, 2026Mar 31, 2026

• skills

  Public
  Public agent skills catalog for Harbor

  Apache License 2.0

  •1•3•0•0•Updated Mar 27, 2026Mar 27, 2026

• harbor-cookbook

  Public
  Realistic examples of building evals and optimizing agents with Harbor

  Python

  •

  Apache License 2.0

  •3•37•0•0•Updated Mar 27, 2026Mar 27, 2026

• terminal-bench-challenges

  Public
  Shell

  •3•0•0•2•Updated Mar 26, 2026Mar 26, 2026

• awesome-harbor

  Public
  A curated list of awesome Harbor ecosystem projects

  2•22•0•1•Updated Mar 16, 2026Mar 16, 2026

• terminal-bench

  Public
  A benchmark for LLMs on complicated tasks in the terminal

  Python

  •

  Apache License 2.0

  •498•1.9k•107•186•Updated Jan 22, 2026Jan 22, 2026