RepoAgent

An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.

Stars: 425

Visit

RepoAgent is an LLM-powered framework designed for repository-level code documentation generation. It automates the process of detecting changes in Git repositories, analyzing code structure through AST, identifying inter-object relationships, replacing Markdown content, and executing multi-threaded operations. The tool aims to assist developers in understanding and maintaining codebases by providing comprehensive documentation, ultimately improving efficiency and saving time.

README:

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

English readme • 简体中文 readme

📺 Demo

👾 Background

In the realm of computer programming, the significance of comprehensive project documentation, including detailed explanations for each Python file, cannot be overstated. Such documentation serves as the cornerstone for understanding, maintaining, and enhancing the codebase. It provides essential context and rationale for the code, making it easier for current and future developers to comprehend the purpose, functionality, and structure of the software. It not only facilitates current and future developers in grasping the project's purpose and structure but also ensures that the project remains accessible and modifiable over time, significantly easing the learning curve for new team members.

Traditionally, creating and maintaining software documentation demanded significant human effort and expertise, a challenge for small teams without dedicated personnel. The introduction of Large Language Models (LLMs) like GPT has transformed this, enabling AI to handle much of the documentation process. This shift allows human developers to focus on verification and fine-tuning, greatly reducing the manual burden of documentation.

🏆 Our goal is to create an intelligent document assistant that helps people read and understand repositories and generate documents, ultimately helping people improve efficiency and save time.

✨ Features

🤖 Automatically detects changes in Git repositories, tracking additions, deletions, and modifications of files.
📝 Independently analyzes the code structure through AST, generating documents for individual objects.
🔍 Accurate identification of inter-object bidirectional invocation relationships, enriching the global perspective of document content.
📚 Seamlessly replaces Markdown content based on changes, maintaining consistency in documentation.
🕙 Executes multi-threaded concurrent operations, enhancing the efficiency of document generation.
👭 Offer a sustainable, automated documentation update method for team collaboration.
😍 Display Code Documentation in an amazing way. (with document book per project powered by Gitbook)

🚀 Getting Started

Installation Method

Using GitHub Actions

This repository supports GitHub Actions for automating workflows such as building, testing, and deploying. For detailed instructions on setting up and using GitHub Actions with this repository, please refer to the actions/run-repoagent.

Using pip (Recommended for Users)

Install the repoagent package directly using pip:

pip install repoagent

Development Setup Using PDM

If you're looking to contribute or set up a development environment:

Install PDM: If you haven't already, install PDM.
Use CodeSpace, or Clone the Repository:
- Use CodeSpace The easiest way to get RepoAgent enviornment. Click below to use the GitHub Codespace, then go to the next step.
- Clone the Repository
```
git clone https://github.com/LOGIC-10/RepoAgent.git
cd RepoAgent
```
Setup with PDM
- Initialize the Python virtual environment. Make sure to run the below cmd in /RepoAgent directory:
```
pdm venv create --name repoagent
```
- Activate virtual environment
- Install dependencies using PDM
```
 pdm install
```

Configuring RepoAgent

Before configuring specific parameters for RepoAgent, please ensure that the OpenAI API is configured as an environment variable in the command line:

export OPENAI_API_KEY=YOUR_API_KEY # on Linux/Mac
set OPENAI_API_KEY=YOUR_API_KEY # on Windows
$Env:OPENAI_API_KEY = "YOUR_API_KEY" # on Windows (PowerShell)

Run RepoAgent

Enter the root directory of RepoAgent and try the following command in the terminal:

repoagent run #this command will generate doc, or update docs(pre-commit-hook will automatically call this)
repoagent run --print-hierarchy # Print how repo-agent parse the target repo

The run command supports the following optional flags (if set, will override config defaults):

-m, --model TEXT: Specifies the model to use for completion. Default: gpt-3.5-turbo
-t, --temperature FLOAT: Sets the generation temperature for the model. Lower values make the model more deterministic. Default: 0.2
-r, --request-timeout INTEGER: Defines the timeout in seconds for the API request. Default: 60
-b, --base-url TEXT: The base URL for the API calls. Default: https://api.openai.com/v1
-tp, --target-repo-path PATH: The file system path to the target repository. Used as the root for documentation generation. Default: path/to/your/target/repository
-hp, --hierarchy-path TEXT: The name or path for the project hierarchy file, used to organize documentation structure. Default: .project_doc_record
-mdp, --markdown-docs-path TEXT: The folder path where Markdown documentation will be stored or generated. Default: markdown_docs
-i, --ignore-list TEXT: A list of files or directories to ignore during documentation generation, separated by commas.
-l, --language TEXT: The ISO 639 code or language name for the documentation. Default: Chinese
-ll, --log-level [DEBUG|INFO|WARNING|ERROR|CRITICAL]: Sets the logging level for the application. Default: INFO

You can also try the following feature

repoagent clean # Remove repoagent-related cache
repoagent diff # Check what docs will be updated/generated based on current code change

If it's your first time generating documentation for the target repository, RepoAgent will automatically create a JSON file maintaining the global structure information and a folder named Markdown_Docs in the root directory of the target repository for storing documents.

Once you have initially generated the global documentation for the target repository, or if the project you cloned already contains global documentation information, you can then seamlessly and automatically maintain internal project documentation with your team by configuring the pre-commit hook in the target repository!

Use `pre-commit`

RepoAgent currently supports generating documentation for projects, which requires some configuration in the target repository.

First, ensure that the target repository is a git repository and has been initialized.

git init

Install pre-commit in the target repository to detect changes in the git repository.

pip install pre-commit

Create a file named .pre-commit-config.yaml in the root directory of the target repository. An example is as follows:

repos:
  - repo: local
    hooks:
    - id: repo-agent
      name: RepoAgent
      entry: repoagent
      language: system
      pass_filenames: false # prevent from passing filenames to the hook
      # You can specify the file types that trigger the hook, but currently only python is supported.
      types: [python]

For specific configuration methods of hooks, please refer to pre-commit. After configuring the yaml file, execute the following command to install the hook.

pre-commit install

In this way, each git commit will trigger the RepoAgent's hook, automatically detecting changes in the target repository and generating corresponding documents. Next, you can make some modifications to the target repository, such as adding a new file to the target repository, or modifying an existing file. You just need to follow the normal git workflow: git add, git commit -m "your commit message", git push The RepoAgent hook will automatically trigger at git commit, detect the files you added in the previous step, and generate corresponding documents.

After execution, RepoAgent will automatically modify the staged files in the target repository and formally submit the commit. After the execution is completed, the green "Passed" will be displayed, as shown in the figure below:

The generated document will be stored in the specified folder in the root directory of the target warehouse. The rendering of the generated document is as shown below:

We utilized the default model gpt-3.5-turbo to generate documentation for the XAgent project, which comprises approximately 270,000 lines of code. You can view the results of this generation in the Markdown_Docs directory of the XAgent project on GitHub. For enhanced documentation quality, we suggest considering more advanced models like gpt-4-1106 or gpt-4-0125-preview.

In the end, you can flexibly adjust the output format, template, and other aspects of the document by customizing the prompt. We are excited about your exploration of a more scientific approach to Automated Technical Writing and your contributions to the community.

Exploring chat with repo

We conceptualize Chat With Repo as a unified gateway for these downstream applications, acting as a connector that links RepoAgent to human users and other AI agents. Our future research will focus on adapting the interface to various downstream applications and customizing it to meet their unique characteristics and implementation requirements.

Here we demonstrate a preliminary prototype of one of our downstream tasks: Automatic Q&A for Issues and Code Explanation. You can start the server by running the following code.

pip install repoagent[chat-with-repo]
repoagent chat-with-repo

✅ Future Work

[ ] Generate README.md automatically combining with the global documentation
[ ] Multi-programming-language support Support more programming languages like Java, C or C++, etc.
[x] Local model support like Llama, chatGLM, Qwen, GLM4, etc.

🥰 Featured Cases

Here are featured cases that have adopted RepoAgent.

MiniCPM: An edge-side LLM of 2B size, comparable to 7B model.
ChatDev: Collaborative AI agents for software development.
XAgent: An Autonomous LLM Agent for Complex Task Solving.
EasyRL4Rec: A user-friendly RL library for recommender systems.

📊 Citation

@misc{luo2024repoagent,
      title={RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation}, 
      author={Qinyu Luo and Yining Ye and Shihao Liang and Zhong Zhang and Yujia Qin and Yaxi Lu and Yesai Wu and Xin Cong and Yankai Lin and Yingli Zhang and Xiaoyin Che and Zhiyuan Liu and Maosong Sun},
      year={2024},
      eprint={2402.16667},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

For Tasks:

Click tags to check more tools for each tasks

generate code documentation track code changes analyze code structure update documentation automate documentation process

For Jobs:

software developer technical writer ai engineer documentation specialist project manager

Alternative AI tools for RepoAgent

Similar Open Source Tools

RepoAgent

github

: 425

guidellm

GuideLLM is a powerful tool for evaluating and optimizing the deployment of large language models (LLMs). By simulating real-world inference workloads, GuideLLM helps users gauge the performance, resource needs, and cost implications of deploying LLMs on various hardware configurations. This approach ensures efficient, scalable, and cost-effective LLM inference serving while maintaining high service quality. Key features include performance evaluation, resource optimization, cost estimation, and scalability testing.

github

: 142

lmql

LMQL is a programming language designed for large language models (LLMs) that offers a unique way of integrating traditional programming with LLM interaction. It allows users to write programs that combine algorithmic logic with LLM calls, enabling model reasoning capabilities within the context of the program. LMQL provides features such as Python syntax integration, rich control-flow options, advanced decoding techniques, powerful constraints via logit masking, runtime optimization, sync and async API support, multi-model compatibility, and extensive applications like JSON decoding and interactive chat interfaces. The tool also offers library integration, flexible tooling, and output streaming options for easy model output handling.

github

: 3.4k

VoiceStreamAI

VoiceStreamAI is a Python 3-based server and JavaScript client solution for near-realtime audio streaming and transcription using WebSocket. It employs Huggingface's Voice Activity Detection (VAD) and OpenAI's Whisper model for accurate speech recognition. The system features real-time audio streaming, modular design for easy integration of VAD and ASR technologies, customizable audio chunk processing strategies, support for multilingual transcription, and secure sockets support. It uses a factory and strategy pattern implementation for flexible component management and provides a unit testing framework for robust development.

github

: 547

rosa

ROSA is an AI Agent designed to interact with ROS-based robotics systems using natural language queries. It can generate system reports, read and parse ROS log files, adapt to new robots, and run various ROS commands using natural language. The tool is versatile for robotics research and development, providing an easy way to interact with robots and the ROS environment.

github

: 256

agentok

Agentok Studio is a tool built upon AG2, a powerful agent framework from Microsoft, offering intuitive visual tools to streamline the creation and management of complex agent-based workflows. It simplifies the process for creators and developers by generating native Python code with minimal dependencies, enabling users to create self-contained code that can be executed anywhere. The tool is currently under development and not recommended for production use, but contributions are welcome from the community to enhance its capabilities and functionalities.

github

: 242

crewAI

CrewAI is a cutting-edge framework designed to orchestrate role-playing autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. It enables AI agents to assume roles, share goals, and operate in a cohesive unit, much like a well-oiled crew. Whether you're building a smart assistant platform, an automated customer service ensemble, or a multi-agent research team, CrewAI provides the backbone for sophisticated multi-agent interactions. With features like role-based agent design, autonomous inter-agent delegation, flexible task management, and support for various LLMs, CrewAI offers a dynamic and adaptable solution for both development and production workflows.

github

: 25.2k

llm-on-ray

LLM-on-Ray is a comprehensive solution for building, customizing, and deploying Large Language Models (LLMs). It simplifies complex processes into manageable steps by leveraging the power of Ray for distributed computing. The tool supports pretraining, finetuning, and serving LLMs across various hardware setups, incorporating industry and Intel optimizations for performance. It offers modular workflows with intuitive configurations, robust fault tolerance, and scalability. Additionally, it provides an Interactive Web UI for enhanced usability, including a chatbot application for testing and refining models.

github

: 87

mosec

Mosec is a high-performance and flexible model serving framework for building ML model-enabled backend and microservices. It bridges the gap between any machine learning models you just trained and the efficient online service API. * **Highly performant** : web layer and task coordination built with Rust 🦀, which offers blazing speed in addition to efficient CPU utilization powered by async I/O * **Ease of use** : user interface purely in Python 🐍, by which users can serve their models in an ML framework-agnostic manner using the same code as they do for offline testing * **Dynamic batching** : aggregate requests from different users for batched inference and distribute results back * **Pipelined stages** : spawn multiple processes for pipelined stages to handle CPU/GPU/IO mixed workloads * **Cloud friendly** : designed to run in the cloud, with the model warmup, graceful shutdown, and Prometheus monitoring metrics, easily managed by Kubernetes or any container orchestration systems * **Do one thing well** : focus on the online serving part, users can pay attention to the model optimization and business logic

github

: 808

agents

Polymarket Agents is a developer framework and set of utilities for building AI agents to trade autonomously on Polymarket. It integrates with Polymarket API, provides AI agent utilities for prediction markets, supports local and remote RAG, sources data from various services, and offers comprehensive LLM tools for prompt engineering. The architecture features modular components like APIs and scripts for managing local environments, server set-up, and CLI for end-user commands.

github

: 60

SheetCopilot

SheetCopilot is an assistant agent that manipulates spreadsheets by following user commands. It leverages Large Language Models (LLMs) to interact with spreadsheets like a human expert, enabling non-expert users to complete tasks on complex software such as Google Sheets and Excel via a language interface. The tool observes spreadsheet states, polishes generated solutions based on external action documents and error feedback, and aims to improve success rate and efficiency. SheetCopilot offers a dataset with diverse task categories and operations, supporting operations like entry & manipulation, management, formatting, charts, and pivot tables. Users can interact with SheetCopilot in Excel or Google Sheets, executing tasks like calculating revenue, creating pivot tables, and plotting charts. The tool's evaluation includes performance comparisons with leading LLMs and VBA-based methods on specific datasets, showcasing its capabilities in controlling various aspects of a spreadsheet.

github

: 82

CogAgent

CogAgent is an advanced intelligent agent model designed for automating operations on graphical interfaces across various computing devices. It supports platforms like Windows, macOS, and Android, enabling users to issue commands, capture device screenshots, and perform automated operations. The model requires a minimum of 29GB of GPU memory for inference at BF16 precision and offers capabilities for executing tasks like sending Christmas greetings and sending emails. Users can interact with the model by providing task descriptions, platform specifications, and desired output formats.

github

: 113

LARS

LARS is an application that enables users to run Large Language Models (LLMs) locally on their devices, upload their own documents, and engage in conversations where the LLM grounds its responses with the uploaded content. The application focuses on Retrieval Augmented Generation (RAG) to increase accuracy and reduce AI-generated inaccuracies. LARS provides advanced citations, supports various file formats, allows follow-up questions, provides full chat history, and offers customization options for LLM settings. Users can force enable or disable RAG, change system prompts, and tweak advanced LLM settings. The application also supports GPU-accelerated inferencing, multiple embedding models, and text extraction methods. LARS is open-source and aims to be the ultimate RAG-centric LLM application.

github

: 418

autoarena

AutoArena is a tool designed to create leaderboards ranking Language Model outputs against one another using automated judge evaluation. It allows users to rank outputs from different LLMs, RAG setups, and prompts to find the best configuration of their system. Users can perform automated head-to-head evaluation using judges from various platforms like OpenAI, Anthropic, and Cohere. Additionally, users can define and run custom judges, connect to internal services, or implement bespoke logic. AutoArena enables users to run the application locally, providing full control over their environment and data.

github

: 65

NeMo-Guardrails

NeMo Guardrails is an open-source toolkit for easily adding _programmable guardrails_ to LLM-based conversational applications. Guardrails (or "rails" for short) are specific ways of controlling the output of a large language model, such as not talking about politics, responding in a particular way to specific user requests, following a predefined dialog path, using a particular language style, extracting structured data, and more.

github

: 4.4k

agentok

Agentok Studio is a visual tool built for AutoGen, a cutting-edge agent framework from Microsoft and various contributors. It offers intuitive visual tools to simplify the construction and management of complex agent-based workflows. Users can create workflows visually as graphs, chat with agents, and share flow templates. The tool is designed to streamline the development process for creators and developers working on next-generation Multi-Agent Applications.

github

: 148

For similar tasks

RepoAgent

github

: 425

awesome-ai-coding

Awesome-AI-Coding is a curated list of AI coding topics, projects, datasets, LLM models, embedding models, papers, blogs, products, startups, and peer awesome lists related to artificial intelligence in coding. It includes tools for code completion, code generation, code documentation, and code search, as well as AI models and techniques for improving developer productivity. The repository also features information on various AI-powered developer tools, copilots, and related resources in the AI coding domain.

github

: 637

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 390

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 595

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 953

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 1.2k

griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github

: 2.1k

RepoAgent

README:

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

📺 Demo

👾 Background

✨ Features

🚀 Getting Started

Installation Method

Using GitHub Actions

Using pip (Recommended for Users)

Development Setup Using PDM

Configuring RepoAgent

Run RepoAgent

Use pre-commit

Exploring chat with repo

✅ Future Work

🥰 Featured Cases

📊 Citation

For Tasks:

For Jobs:

Alternative AI tools for RepoAgent

Similar Open Source Tools

RepoAgent

guidellm

lmql

VoiceStreamAI

rosa

agentok

crewAI

llm-on-ray

mosec

agents

SheetCopilot

CogAgent

LARS

autoarena

NeMo-Guardrails

agentok

For similar tasks

RepoAgent

awesome-ai-coding

For similar jobs

sweep

teams-ai

ai-guide

classifai

chatbot-ui

BricksLLM

uAgents

griptape

Use `pre-commit`