- Category
- Developer Tools
- Rank
- No. 2040Tools index
- Pricing
- Open Source
- Type
- TOOL
- Use case
- Model & Agent Evaluation
- GitHub
- 1 stars
- Latest release
- v0.1.0
- Date
About
Bugbout benchmarks coding agents on your own codebase. It mines fixes in your git history that name an issue and add a test, gives each agent the pre-fix checkout in a sandbox, and scores the resulting patches with the maintainers' hidden tests. It also runs each agent's tests against the others' patches, so you can judge whether agents could review one another.
Why it made the leaderboard
It lets teams measure which coding agent actually fixes bugs in their specific codebase and conventions, instead of trusting a public benchmark that may not reflect their stack.
Tags
coding-agentbenchmarkevaluationtestingpythoncli
Tech Stack
Python
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.