Popular repositories Loading
-
radar-bench
radar-bench PublicExecutable benchmark for evaluating whether software-engineering agents can diagnose dependency and version regressions without falsely blaming upstream projects.
Python
-
-
GreenGap
GreenGap Public archiveArchived — static Plan-mode analyzer for finding pytest tests CI did not plan to run. Final release v0.1.4.
Python
-
Lasso
Lasso PublicLASSO turns human visual selections into live typed WebMCP capability contracts for AI agents.
JavaScript
-
computelab-release-assurance
computelab-release-assurance PublicEvidence-driven release qualification for OpenAI-compatible LLM deployments.
Python
-
humanerror
humanerror PublicHUMAN ERROR — a one-screen microgame rush with 132 deterministic missions and server-replayed leaderboard scoring. Built for Hackyard Yard #3.
TypeScript
If the problem persists, check the GitHub status page or contact support.

