Crit – Review AI agent work like you review PRs
Finally solves the pain of reviewing 1000-line agent plans without losing context between iterations.
A tool for automating quarterly, semi-annual, and annual reviews. Automatically get your GitHub contributions and align them to your team and company's goals.
GitHub PRs to performance reviews with local Ollama support for privacy.
Software engineers, engineering managers
Lattice · 15Five · Culture Amp
It fetches your PRs, code review activity, and commits, then generates a structured review.
You can point it at a goals markdown file to align your work to team/company OKRs, and add a separate achievements file for non-GitHub work (mentoring, incidents, interviews, etc.).
Supports Anthropic, OpenAI, and Ollama.
Finally solves the pain of reviewing 1000-line agent plans without losing context between iterations.
Local PR UI exports inline comments as XML for agents to fix automatically.
Claude in GitHub Actions with inline comments, but Codiumai and others already own this niche.
Commit-by-commit PR replay beats flat diffs for understanding AI agent intent.
Privacy-first PR dashboard that runs entirely in your browser, no accounts.
The product's real selling point is the iterative verification loop: AI inspects PRs/branches, surfaces exploitable issues with file+line and severity, and then re-runs reviews to confirm fixes — that workflow (Open → In Progress → Resolved → Closed/Rejected) is practical and would reduce issues slipping through. Promising as a unified place for docs, review, security and perf, but success depends heavily on low false-positive rates and transparent evidence for security findings; without that, it risks feeling like another noisy scanner.