Neura Market
ReviewCerberus logo

ReviewCerberus

Free

Open-source AI code review tool for analyzing git branch differences with comprehensive security, performance, and quality analysis.

FreeFree tier
Type
Open Source
Visit Website GitHub (38 stars)

About ReviewCerberus

ReviewCerberus is an open-source AI-powered code review tool that analyzes git branch differences to generate comprehensive review reports with structured output. It integrates as a GitHub Action for automated pull request reviews with inline comments and summary, supports multiple AI providers including AWS Bedrock, Anthropic API, Ollama, and Moonshot, and offers detailed analysis covering logic correctness, security vulnerabilities, performance bottlenecks, and code quality. Additional experimental features include a Chain-of-Verification mode to reduce false positives and a SAST pre-scan. The tool leverages prompt caching for smart token efficiency and can be run via Docker or directly using Poetry. Reports can be output as Markdown or JSON.

Key Features

GitHub Action integration for automated PR reviews with inline comments and summary
Comprehensive analysis of logic correctness, security (OWASP), performance (N+1 queries, bottlenecks), and code quality
Structured output with issues organized by severity and summary table
Multi-provider support: AWS Bedrock, Anthropic API, Ollama, or Moonshot
Smart analysis with prompt caching for token efficiency
Git integration supporting commit hashes and any repository
Experimental Chain-of-Verification mode to reduce false positives
Experimental SAST pre-scan for additional security analysis
Docker support for easy deployment
Output in Markdown or JSON format

Pros & Cons

Pros
  • Open-source and free to use
  • Supports multiple AI providers (Anthropic, AWS, Ollama, Moonshot) for flexibility
  • Provides structured, severity-organized review reports
  • Seamless GitHub Action integration for automated PR comments
  • Comprehensive coverage of logic, security, performance, and quality
  • Docker deployment simplifies setup
  • Experimental verification mode helps reduce false positives
Cons
  • Experimental features (verification, SAST) may be unstable
  • Requires API keys and configuration for AI providers
  • Limited community adoption (32 stars, 2 forks as of writing)
  • No explicit support for non-git workflows or single-file analysis
  • Documentation and examples somewhat minimal

Best For

Automated code review for pull requests in CI/CD pipelinesSecurity auditing and vulnerability detection in code changesPerformance optimization by identifying bottlenecks and N+1 queriesCode quality enforcement and adherence to best practicesQuick review of git branch differences before mergingIntegration into development workflows via GitHub Actions

FAQ

Which AI providers does ReviewCerberus support?
It supports AWS Bedrock, Anthropic API, Ollama, and Moonshot as backends for code review analysis.
How can I run ReviewCerberus on my project?
The easiest way is via Docker using the command `docker run --rm -it -v $(pwd):/repo -e MODEL_PROVIDER=anthropic -e ANTHROPIC_API_KEY=sk-ant-your-api-key kirill89/reviewcerberus:latest --repo-path /repo --output /repo/review.md`. Alternatively, you can use it as a GitHub Action by adding a workflow file.
Is ReviewCerberus free to use?
Yes, it is open-source and free. You only pay for the AI provider API usage if you use cloud services like Anthropic or AWS Bedrock.