10 open-source repos that review your code with AI, from Alibaba to Anthropic
victor_explore · x · 2026-11-10
A curated thread lists 10 open-source GitHub repos that bring AI code review into pull requests (stars checked Oct 2026):
- alibaba/open-code-review (4.4k★): hybrid architecture of deterministic pipelines + LLM agent with precise line-level comments, battle-tested at Alibaba scale
- The-PR-Agent/pr-agent (16k★): the original open-source PR reviewer with /review and /improve commands
- anthropics/claude-code-action (9k★): @claude reviews your pull requests
- anthropics/claude-code-security-review (6k★): security-focused review for vulnerability detection
- mattzcarey/shippie (3k★, formerly Code Review GPT): explores the codebase before commenting, keeping only human-relevant feedback
- google-github-actions/run-gemini-cli (2k★): Gemini CLI for PR reviews, triage, and code analysis
- awesome-skills/code-review-skill (2k★): a modular code review skill with checklists for Claude Code
- kenn-io/roboREV (2k★): reviews every commit in the background
- kodustech/kodus (1k★): self-hosted PR reviewer
- openai/codex-action (1k★): run Codex in GitHub Actions
More from coding & agent
- Agents build Lean models of every CPython 3.15.2 function, validated on 50,000+ generated inputs — ChrSzegedy · 2026-11-10
- The dialectics of AI coding: LLMs can't write prod code unsupervised — neither can humans — ShenRaphael · 2026-11-10
- SteerCamp's multi-agent crew holds daily standups, reporting progress and blockers like employees — pramodk73 · 2026-11-10
- Running Codex for two days to reimplement an outdated Android book's projects and retake screenshots — burkov · 2026-11-10
- Unverified: Fable 5.2 tops FrontierCode 2.0 at 49.1%, half the cost of Opus — FinanceYF5 · 2026-11-10
- Mnemos memory system gives Claude cross-session mood continuity, dev claims — RileyRalmuto · 2026-11-10