Harbor

Pinned Loading

1. terminal-bench-1 terminal-bench-1 Public

   A benchmark for LLMs on complicated tasks in the terminal

   Python 2.6k 572

2. harbor harbor Public

   Framework for evaluating and improving agents

   Python 5.9k 1.9k

3. terminal-bench-2 terminal-bench-2 Public

   Shell 421 116

4. terminal-bench terminal-bench Public

   Measuring and evolving with the frontier of agent work

   Python 850 557

5. terminal-bench-science terminal-bench-science Public

   Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains

   Python 677 441

6. awesome-harbor awesome-harbor Public

   A curated list of awesome Harbor ecosystem projects

   54 4