Search papers, labs, and topics across Lattice.
RepoReviewer, a multi-agent system, is introduced for automated GitHub repository review, addressing limitations of single-pass approaches by decomposing the review process into distinct stages such as repository acquisition, context synthesis, and file-level analysis. The system leverages LangGraph for orchestration and provides both a Python CLI and FastAPI API for developer interaction. By offering a modular architecture and reusable evaluation infrastructure, RepoReviewer facilitates more targeted and efficient code reviews while enabling future empirical studies.
RepoReviewer tackles the complexity of repository-level code review with a multi-agent architecture, breaking down the monolithic process into manageable stages for more relevant and efficient feedback.
Repository-level code review requires reasoning over project structure, repository context, and file-level implementation details. Existing automated review workflows often collapse these tasks into a single pass, which can reduce relevance, increase duplication, and weaken prioritization. We present RepoReviewer, a local-first multi-agent system for automated GitHub repository review with a Python CLI, FastAPI API, LangGraph orchestration layer, and Next.js user interface. RepoReviewer decomposes review into repository acquisition, context synthesis, file-level analysis, finding prioritization, and summary generation. We describe the system design, implementation tradeoffs, developer-facing interfaces, and practical failure modes. Rather than claiming benchmark superiority, we frame RepoReviewer as a technical systems contribution: a pragmatic architecture for repository-level automated review, accompanied by reusable evaluation and reporting infrastructure for future empirical study.
