Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
ChatPilot: Chat Agent Web UI,实现Chat对话前端,支持Google搜索、文件网址对话(RAG)、代码解释器功能,复现了Kimi Chat(文件,拖进来;网址,发出来)。
| Date | Stars |
|---|---|
| 2026-07-31 | 600 |
| 2026-08-01 | 600 |
| 2026-08-06 | 600 |
| 2026-08-11 | 602 |
| 2026-08-18 | 602 |
| 2026-09-20 | 602 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
[**🇨🇳中文**](https://github.com/shibing624/ChatPilot/blob/main/README.md) | [**🌐English**](https://github.com/shibing624/ChatPilot/blob/main/README_EN.md)
<div align="center">
<a href="https://github.com/shibing624/ChatPilot">
<img src="https://github.com/shibing624/ChatPilot/blob/main/docs/favicon.png" height="150" alt="Logo">
</a>
</div>
-----------------
# ChatPilot: Chat Agent Web UI
[](https://badge.fury.io/py/ChatPilot)
[](https://pepy.tech/project/ChatPilot)
[](CONTRIBUTING.md)
[](LICENSE)
[](requirements.txt)
[](https://github.com/shibing624/ChatPilot/issues)
[](#Contact)
**ChatPilot**: Chat Agent WebUI, 实现了AgentChat对话,支持Google搜索、文件网址对话(RAG)、代码解释器功能,复现Kimi Chat(文件,拖进来;网址,发出来),支持OpenAI/Azure API。
## Features
- 本项目基于[Agentica](https://github.com/shibing624/agentica)实现了Agent Assistant调用,支持如下功能:
- 工具调用:支持Agent调用外部工具
- 联网搜索工具:Google Search API(Serper/DuckDuckGo)
- URL自动解析工具:复现了Kimi Chat网址发出来功能
- Python代码解释器:支持E2B虚拟环境和本地python编译器环境运行代码
- 多种LLM接入:支持多种LLM模型以多方式接入,包括使用Ollama Api接入各种本地开源模型;使用litellm Api接入各云服务部署模型;使用OpenAI Api接入GPT系列模型
- RAG:支持Agent调用RAG文件问答
- 支持前后端服务分离,前端使用Svelte,后端使用FastAPI
- 支持语音输入输出,支持图像生成
- 支持用户管理,权限控制,支持聊天记录导入导出
## Demo
Official Demo: https://chat.mulanai.com

## Getting Started
### Run ChatPilot in Docker
```shell
export OPENAI_API_KEY=sk-xxx
export OPENAI_BASE_URL=https://xxx/v1
docker run -it \
-e OPENAI_API_KEY=$WORKSPACE_BASE \
-e OPENAI_BASE_URL=$OPENAI_BASE_URL \
-e RAG_EMBEDDING_MODEL="text-embedding-ada-002" \
-p 8080:8080 --name chatpilot-$(date +%Y%m%d%H%M%S) shibing624/chatpilot:0.0.1
```
You'll find ChatPilot running at http://0.0.0.0:8080 Enjoy! 😄
### 本地启动服务
```shell
git clone https://github.com/shibing624/ChatPilot.git
cd ChatPilot
pip install -r requirements.txt
# Copying required .env file, and fill in the LLM api key
cp .env.example .env
bash start.sh
```
好了,现在你的应用正在运行:http://0.0.0.0:8080 Enjoy! 😄
### 构建前端web
两种方法构建前端:
1. 解压打包并编译好的前端 [web/build.zip](https://github.com/shibing624/ChatPilot/web/build.zip),解压到项目web目录下。
2. 如果修改了web前端代码,需要自己使用npm重新构建前端:
```sh
git clone https://github.com/shibing624/ChatPilot.git
cd ChatPilot/
# Building Frontend Using Node.js >= 20.10
cd web
npm install
npm run build
```
输出:项目`web`目录产出`build`文件夹,包含了前端编译输出文件。
### 多种LLM接入
#### 使用OpenAI Api接入GPT系列模型
- 使用OpenAI API,配置环境变量:
```shell
export OPENAI_API_KEY=xxx
export OPENAI_BASE_URL=https://api.openai.com/v1
export MODEL_TYPE="openai"
```
- 如果使用Azure OpenAI API,需要配置如下环境变量:
```shell
export AZURE_OPENAI_API_KEY=
export AZURE_OPENAI_API_VERSION=
export AZURE_OPENAI_ENDPOINT=
export MODEL_TYPE="azure"
```
#### 使用Ollama Api接入各种本地开源模型
以`ollama serve`启动ollama服务,然后配置`OLLAMA_API_URL`:`export OLLAMA_API_URL=http://localhost:11413`
#### 使用litellm Api接入各云服务部署模型
1. 安装`litellm`包:
```shell
pip install litellm -U
```
2. 修改配置文件
`chatpilot`默认的litellm config文件在`~/.cache/chatpilot/data/litellm/config.yaml`
修改其内容如下:
```yaml
model_list:
# - model_name: moonshot-v1-auto # show model name in the UI
# litellm_params: # all params accepted by litellm.completion() - https://docs.litellm.ai/docs/completion/input
# model: openai/moonshot-v1-auto # MODEL NAME sent to `litellm.completion()` #
# api_base: https://api.moonshot.cn/v1
# api_key: sk-xx
# rpm: 500 # [OPTIONAL] Rate limit for this deployment: in requests per minute (rpm)
- model_name: deepseek-ai/DeepSeeExcerpt of 5,919 characters
Read on GitHubMing Xu (徐明) · @tencent · China
173
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d17ad8601451c241, topic:chatbot, topic:chatgpt, desc:web ui