Code Review Agent
Juadsuarezsan/code-review-agent
Revisor automático de PRs com detecção de bugs e análise de cobertura de testes
Ver no GitHubAgent de revisão de código que analisa pull requests usando tree-sitter, análise estática e Claude para detectar bugs, sugerir refatorações, identificar gaps de testes e gerar comentários inline automáticos. Integra-se com GitHub Actions e é avaliado contra SWE-bench Lite.
Instalação
npx convez-ai Juadsuarezsan/code-review-agent1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Automatizar revisão de código em pull requests no GitHub
- Detectar bugs e problemas de segurança antes do merge
- Identificar gaps de testes e sugerir cobertura
- Gerar comentários inline contextualizados com justificativas
Veredito

Projeto ambicioso que combina análise estática (tree-sitter, ruff, semgrep) com Claude para revisão semântica real. Ainda em fase de planejamento, mas a arquitetura é sólida e o roadmap claro — útil para times que querem CI/CD mais inteligente e menos ruído que ferramentas convencionais.
README
A tradução para o português deste README ainda está na fila.
Project 06 — Code Review Agent
Analyzes pull requests, detects real bugs, suggests refactorizations, writes missing tests, comments inline on the diff. The space behind Copilot Workspace, Cursor, Codium, Sourcegraph Cody.
Industrial use case: Developer tools — Cursor, Codium, Sourcegraph Cody, Codacy.
What this project does
Reads a PR (diff + context), runs multiple analyzers in parallel (bug detector, style checker, test gap analyzer, security scanner, performance reviewer), synthesizes the top-N most actionable comments by severity. Posts inline comments to GitHub via Actions.
Architecture
PR (GitHub webhook or manual input)
│
▼
[PR Analyzer] PyGithub → changed files, lines, context
│
▼
[Context Builder]
├─ AST via tree-sitter
├─ related files (imports, importers)
├─ git history
└─ linked issue
│
▼
[Multi-aspect Analyzers] (parallel)
├─ Bug Detector (Claude + static analysis)
├─ Style Checker (ruff/eslint + Claude)
├─ Test Gap Analyzer (Claude)
├─ Security Scanner (semgrep + Claude)
└─ Performance Reviewer (Claude)
│
▼
[Comment Synthesizer] Claude → inline comments
│ location, severity, suggestion, justification
│
▼
[Priority Filter] → top N by severity
│
▼
[Output] post to GitHub or return JSON
Roadmap to v1.0.0
- PyGithub integration for PR reading + commenting
- tree-sitter for multi-language AST (Python, JS/TS, Go)
- Static analysis wrappers (ruff, mypy, eslint, semgrep)
- LangGraph parallel analyzer pipeline
- Comment synthesizer with severity scoring
- Eval on SWE-bench Lite (300 issues) — bug detection F1
- LLM-as-judge on 100 generated comments (actionability, specificity, correctness)
- Next.js demo with diff viewer (react-diff-viewer)
- Gallery of 10 reviews on famous public PRs
- GitHub Action published to marketplace for self-hosted use
Stack
| Layer | Technology |
|---|---|
| LLM | Claude Sonnet 4.5 |
| AST | tree-sitter (Python, JS/TS, Go bindings) |
| Static analysis | pylint, ruff, mypy (Python), ESLint (JS/TS) |
| Security | semgrep |
| Diff parsing | unidiff or difflib |
| GitHub | PyGithub |
| Orchestration | LangGraph |
| Storage | PostgreSQL for historical reviews |
| Frontend | Next.js with react-diff-viewer |
| Observability | LangSmith |
Definition of Done — project-specific
- Pipeline runs over all 300 SWE-bench Lite issues
- Bug detection F1 reported against ground truth fixes
- Comment quality LLM-judged over 100 cases
- Demo: paste a diff or PR URL, see review generated
- Gallery of 10 reviews on famous public PRs in the demo
- GitHub Action published to the marketplace for use in real repos
- Cost-vs-quality analysis: when is this worth it vs ruff alone
Plus the 12 universal DoD blocks.
License
MIT.