performance-regression

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

Build trustworthy pytest-benchmark matrices, collect repeated runs, and detect performance regressions

LLM agent that turns two Android Perfetto traces and a git range into a cited diagnosis: the regressed metric, the culprit commit, and the trace rows that prove it. Every claim is re-verified by code; measured on planted regressions.

Evidence-backed performance regression guardrails for pull requests, with protected verification and bounded Codex repair workflows.

Profile a pytest suite, script, or callable and comment a CPU + memory hotspot diff on every pull request.

Compare Rust benchmark results across pull-request revisions