Open Issues Need Help
View All on GitHub [0.8] Evaluate harness policies with same-agent ablations and overhead measurements about 1 month ago
enhancement help wanted
Validate AI execution profiling on real non-agent workloads with reproducible evidence bundles about 1 month ago
enhancement help wanted
Publish a reproducible cross-workload benchmark for AgentLoop usefulness about 1 month ago
enhancement help wanted
enhancement help wanted
Export self-contained static HTML analysis reports about 2 months ago
enhancement help wanted good first issue
Make quality scorer names match their actual semantics about 2 months ago
bug help wanted
bug help wanted
Create a reusable integration conformance suite 2 months ago
enhancement help wanted
enhancement help wanted
enhancement help wanted
enhancement help wanted
bug help wanted
Escape trace-derived content in Markdown exporters 4 months ago
bug good first issue code-quality
bug good first issue python
Rename or implement the auto-instrument command 4 months ago
enhancement good first issue python