Show HN: AI-powered code review tool
ReviewCerberus is an AI-powered code review tool that analyzes git branch differences and produces structured review reports. It offers features such as GitHub Action integration, multi‑provider model support, and experimental verification and SAST modes. The tool can be run via Docker or command‑line commands and outputs results in markdown or JSON format.
- ▪The tool supports model providers including AWS Bedrock, Anthropic API, Ollama, and Moonshot, and can be invoked as a GitHub Action for automated pull‑request reviews.
- ▪ReviewCerberus generates a summary, severity‑rated issue table, and detailed explanations with suggested fixes for logic, security, performance, and code quality concerns.
- ▪An experimental verification mode uses a chain‑of‑verification process to reduce false positives, while an optional SAST pre‑scan leverages an OpenGrep (Semgrep fork) scanner.
- ▪Users can customize target branches, output locations, review guidelines, and enable verification or SAST flags via simple command‑line options.
Opening excerpt (first ~120 words) tap to expand
ReviewCerberus AI-powered code review tool that analyzes git branch differences and generates comprehensive review reports with structured output. Key Features GitHub Action: Automated PR reviews with inline comments and summary 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 to reduce false positives Quick Start Run with Docker (recommended): docker run --rm -it -v $(pwd):/repo \ -e MODEL_PROVIDER=anthropic \ -e…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.