Show HN: Free open source AI+SAST code review tool for GitHub Actions

ReviewCerberus, a free open source AI-powered code review tool for GitHub Actions, has been released. It analyzes git branch differences and generates comprehensive review reports covering logic, security, performance, and code quality with structured output. The tool supports multiple AI providers including AWS Bedrock, Anthropic API, Ollama, and Moonshot.

ReviewCerberus AI-powered code review tool that analyzes git branch differences and generates comprehensive review reports with structured output. Quick Start That's it The review will be saved to review.md in your current directory. Key Features Comprehensive Reviews : Detailed analysis of logic, security, performance, and code quality Structured Output : Issues organized by severity with summary table Multi-Provider : AWS Bedrock, Anthropic API, Ollama, or Moonshot Smart Analysis : Context provided upfront with prompt caching Git Integration : Works with any repository, supports commit hashes Verification Mode : Experimental Chain-of-Verification https://arxiv.org/abs/2309.11495 to reduce false positives Usage Examples Custom target branch: With custom review guidelines: What's Included Comprehensive Code Review Detailed analysis covering: - Logic & Correctness: Bugs, edge cases, error handling - Security: OWASP issues, access control, input validation - Performance: N+1 queries, bottlenecks, scalability - Code Quality: Duplication, complexity, maintainability - Side Effects: Impact on other system parts - Testing: Coverage gaps, missing test cases - Documentation: Missing or outdated docs Structured Output Every review includes: Summary : High-level overview of changes and risky areas Issues Table : All issues at a glance with severity indicators 🔴 CRITICAL, 🟠 HIGH, 🟡 MEDIUM, 🟢 LOW Detailed Issues : Each issue with explanation, location, and suggested fix Configuration Anthropic API AWS Bedrock default Ollama local models Moonshot Command-Line Options --target-branch : Branch to compare against - default: main --output : Output file path or directory --repo-path : Path to git repository - default: /repo --instructions : Path to markdown file with custom review guidelines --verify : Enable verification mode to reduce false positives experimental --sast : Enable OpenGrep SAST pre-scan experimental --json : Output review as JSON instead of markdown Requirements - Git repository mounted to /repo - Either Anthropic API key or AWS Bedrock credentials - Output directory must be writable Links License MIT