RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation

TL;DR

RepoAgent is an open-source framework leveraging large language models to automatically generate, maintain, and update comprehensive repository-level code documentation, addressing a gap in AI-assisted software documentation.

Contribution

It introduces RepoAgent, a novel LLM-powered framework specifically designed for proactive and high-quality repository-level code documentation generation.

Findings

Outperforms existing methods in documentation quality

Effective in maintaining and updating documentation

Validated through comprehensive evaluations

Abstract

Generative models have demonstrated considerable potential in software engineering, particularly in tasks such as code generation and debugging. However, their utilization in the domain of code documentation generation remains underexplored. To this end, we introduce RepoAgent, a large language model powered open-source framework aimed at proactively generating, maintaining, and updating code documentation. Through both qualitative and quantitative evaluations, we have validated the effectiveness of our approach, showing that RepoAgent excels in generating high-quality repository-level documentation. The code and results are publicly accessible at https://github.com/OpenBMB/RepoAgent.