Open Issues Need Help
View All on GitHub Show latest GET /eval pass rate on the embedded dashboard about 2 hours ago
enhancement help wanted
MIT-licensed research lab for measurable LLM reasoning — evals, routing, and a live Cloudflare Worker dashboard.
TypeScript
#ai-research#bleujs#cloudflare-workers#evals#evaluation#llm#mit-license#open-source#reasoning#typescript
Add one logic-puzzle eval task with expected pass criteria about 2 hours ago
enhancement good first issue
MIT-licensed research lab for measurable LLM reasoning — evals, routing, and a live Cloudflare Worker dashboard.
TypeScript
#ai-research#bleujs#cloudflare-workers#evals#evaluation#llm#mit-license#open-source#reasoning#typescript