Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Peng Zhang

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.

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

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.
Paper Structure (23 sections, 2 figures, 1 table)

This paper contains 23 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Problem Setting
  3. System Overview
  4. Design Principles
  5. ClonerAgent
  6. ContextAgent
  7. ReviewAgent
  8. PriorityAgent
  9. SummaryAgent
  10. Implementation
  11. Component Boundaries
  12. Output Artifacts
  13. Demonstration and Analysis
  14. Demonstration Scenarios
  15. Illustrative Examples
  16. ...and 8 more sections

Figures (2)

  • Figure 1: RepoReviewer system architecture showing user-facing interfaces, the LangGraph workflow, external provider and GitHub integrations, and local artifact generation.
  • Figure 2: RepoReviewer web interface across job submission, staged agent execution, and final artifact rendering.