Pinned Loading

1. Debug-Brief Debug-Brief Public

   Local-first CLI that turns a debugging session into an honest markdown brief for PRs, handoffs and incidents

   Python 9 1

2. code-review-arena code-review-arena Public

   Execution-backed benchmark for AI code-review agents. Applies each suggested fix, runs the required tests and validators, and scores detection separately from validation.

   Python

3. contamination-checker contamination-checker Public

   ContamCheckr: a local, CPU-friendly auditor for benchmark contamination evidence in causal language models.

   Python

4. Helm-browser-agent Helm-browser-agent Public

   Drive a real browser with plain English: structured intent, validated actions, and a Groq/Gemini/Ollama fallback cascade on Playwright.

   Python