Agent-Field/pr-af
#1 open-source code reviewer on Code-Review-Bench
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #301 of 3,103 repositories GStars tracks this week (top 10%).
The project lists 6 contributors on GitHub.
Use Cases & Benefits
- Provides an open-source AI-driven code review system that performs deep, evidence-grounded analysis of pull requests using agentic multi-phase pipelines.
- Delivers highly accurate, compound-aware code reviews with extremely low false positives by dynamically spawning specialized reviewer agents and grounding findings in code evidence.
- Use for integrating comprehensive, automated architectural audits into CI/CD pipelines to gate pull requests with rigorous code quality checks.
- Use for self-hosted code review automation that supports flexible model selection to balance cost and review depth for different PR complexities.
- Use for research or benchmarking of AI code review tools with reproducible results and open model usage in a parallel cognitive pipeline architecture.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
No license detected
No license file detected by GitHub: unless the project grants one elsewhere, the default is all rights reserved.
Community files
- README: present
Watch-outs
- Warning: No license file detected by GitHub: unless the project grants one elsewhere, you generally have no permission to use, modify or distribute the code.
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
PR-AF is the #1 open-source code reviewer on Martian Code-Review-Bench. It is built for deep code review, not shallow diff summaries: turn each PR into a task-specific review plan, spawn focused reviewer agents, ground findings in code evidence, challenge the results, and squeeze more useful review intelligence out of cheaper models. Run DeepSeek-class models for routine PRs, GLM-5.2 for deep open-model reviews, or Opus-class frontier models for major PRs — where PR-AF tops the benchmark by a wide margin.
On the 38 runnable Martian Code-Review-Bench PRs, PR-AF with GLM-5.2 is the #1 open-source reviewer in golden recall: 0.706 across 42 compared tools. It is ahead of cubic-v2 and every qodo, coderabbit, greptile, copilot, and devin variant in this snapshot.
Full benchmark package:
benchmark/martian-code-review-bench.Trigger it with the
afCLI (requires af ≥ 0.1.87) — it streams live progress and prints the result:Prefer raw HTTP? Hit the API directly with curl:
Posts inline GitHub review comments with evidence-grounded findings:
Custom review strategy per PR. Evidence-grounded findings. About 10× cheaper per review than closed-source tools.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+206 stars over 73 days across 13 snapshot days; best day +48 on Aug 12.
Forks
75+32
Open issues
4-2
Compared with peers in AI
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| storytold/artcraft | 35.6K | +6.7K | 75 | 26 days ago |
| heygen-com/hyperframes | 70.8K | +5.6K | 45 | today |
| Comfy-Org/ComfyUI | 142.4K | +4.5K | 60 | 4 days ago |
| Leonxlnx/taste-skill | 101.6K | +3.8K | 75 | 3 days ago |
| harry0703/MoneyPrinterTurbo | 134.2K | +2.9K | 75 | 1 day ago |
| Agent-Field/pr-af | 657 | +0 | 75 | — |
| Category median | 101.6K | +4.5K | 75 | — |
Also by Agent-Field
Other repositories from this maintainer that GStars tracks
Discover Repositories
Search across tracked repositories by name or description