This project is an Github AI assistant built using LangGraph, FastAPI, and Streamlit, designed to interact with GitHub through its GraphQL API.
# 🧰 Github AI Assistant
<h4 align="center">
<p>
<b>English</b> |
<a href="https://github.com/wanzunz/chat_with_github/blob/main/README_CN.md">中文(简体)</a>
<p>
</h4>
An AI assistant that simultaneously supports a range of capabilities within GitHub, such as querying/modifying repositories, organizations, Issues, Pull Requests, and more. Theoretically, it supports most of the capabilities documented in the [GitHub GraphQL API documentation](https://docs.github.com/en/graphql).
This project is derived from modifications to [JoshuaC215/agent-service-toolkit](https://github.com/JoshuaC215/agent-service-toolkit).
It includes a [LangGraph](https://langchain-ai.github.io/langgraph/) agent, a [FastAPI](https://fastapi.tiangolo.com/) service to serve it, a client to interact with the service, and a [Streamlit](https://streamlit.io/) app that uses the client to provide a chat interface. Data structures and settings are built with [Pydantic](https://github.com/pydantic/pydantic).
This project offers a template for you to easily build and run your own agents using the LangGraph framework. It demonstrates a complete setup from agent definition to user interface, making it easier to get started with LangGraph-based projects by providing a full, robust toolkit.
## Overview
### What Can It Do?
- Support for Various Query Operations

- Support for Various Modification Operations

### More Features
#### Example 1: Automatically Generate and Modify Repository Descriptions
`The English version always doesn't execute as expected, not sure why, maybe it's the model's issue. So here are only screenshots in Chinese.`
Modify the description of my repository wanzunz/my_repo by fetching the README.md file, summarizing it, and generating a description within 120 words.

#### Example 2: Reply to Issues with Documentation ReHAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型