RepoReviewer: A Local-First Multi-Agent Architecture for Repository-Level Code Review

TL;DR

RepoReviewer is a multi-agent system designed for comprehensive repository-level code review, integrating various analysis stages through a modular architecture to improve relevance and prioritization in automated reviews.

Contribution

It introduces a pragmatic, multi-agent architecture for repository-level code review, with reusable infrastructure for future empirical evaluation.

Findings

Decomposes review into distinct stages for better analysis

Provides a practical architecture with reusable evaluation tools

Highlights system design and implementation tradeoffs

Abstract

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.