RepoReviewer: A Local-First Multi-Agent Architecture for Repository-Level Code Review
This addresses the challenge of inefficient automated code review workflows for developers, though it is presented as an incremental technical systems contribution rather than a breakthrough.
The authors tackled the problem of automated repository-level code review by introducing RepoReviewer, a local-first multi-agent system that decomposes review into tasks like repository acquisition and file-level analysis to improve relevance and reduce duplication, but they do not report concrete performance numbers.
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.