Sébastien Rigaux

OpenCodeReview combines deterministic checks with LLM agents

View resource

github.com

OpenCodeReview automates code review by combining deterministic pipelines with an LLM agent. The repository describes a tool that produces precise line-level comments and includes multilingual rules for issues such as null pointer exceptions, thread safety, XSS, and SQL injection.

This hybrid architecture uses explicit rules for checks that can be codified, with the agent as a complement. The tool is compatible with OpenAI and Anthropic APIs.

Green shield-shaped logo surrounding a stylized eye on a white background.