Agents / Coding /
harbor
Made by
Framework for evaluating and improving agents
AGENTRANK SCORE75/100
RANK#474 of 1,604
GITHUB STARS6,250 +216
FORKS2,028
Facts from GitHub
- Repository
- github.com/harbor-framework/harbor
- Maker
- harbor-framework
- Language
- Python
- Licence
- Apache-2.0
- Category
- Coding (auto-categorised)
- Topics
- evals rl-environments terminal-bench
- Created
- Aug 4, 2025
- Last push
- Oct 18, 2026
From the GitHub API, 2026-10-19.
Score breakdown
Popularity ×30%53
Adoption ×20%79
Activity ×25%100
Momentum ×15%51
Openness ×10%100
Computed from public GitHub data. This measures traction and upkeep, not how well the agent does tasks. How the score works
Embed your score
Task benchmark
Not benchmarked
Listing is not an endorsement. This looks like a coding agent, so it can be scored on Task #1 with the open harness.
Something wrong? Report a correction.