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.
Multi-Agent-GPT: 一款基于RAG和agent构建的多模态专家助手GPT。它集成了文本、图像和音频等模态工具。支持本地部署和私有数据库建设。
| Date | Stars |
|---|---|
| 2026-07-31 | 271 |
| 2026-08-05 | 271 |
| 2026-08-06 | 271 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
##
A multimodal expert assistant GPT platform built using RAG+agent. It integrates tools for modalities such as text, images, and audio. Support local deployment and private database construction.
[](https://GitHub.com/Naereen/StrapDown.js/graphs/commit-activity) [](http://makeapullrequest.com)
[Web Video](https://github.com/YangXuanyi/Multi-Agent-GPT/assets/83216339/30e76e97-d02e-4a18-b5e1-896be99d5564)
</div>
## 💡 1 RoadMap
`1` Basic Function
- [x] Single/multi turn chat
- [x] Multimodal information display and interaction
- [x] Agent
- [x] Tools
- [x] Web searching
- [x] Image generation
- [x] Image caption
- [ ] audio-to-text
- [ ] text-to-audio
- [ ] Video caption
- [ ] RAG
- [ ] Private database
- [ ] Offline deployment
`2` Supporting Information Modality
- [x] text
- [x] image
- [ ] audio
- [ ] video
`3` Model Interface API
- [x] ChatGPT
- [x] Dalle
- [x] Google-Search
- [x] BLIP
## 👨💻 2 Development
Project technology stack: Python + torch + langchain + gradio
### **⚡ 2.1 Installation**
1. Create a virtual environment in Anaconda:
```
conda create -n agent python=3.10
```
2. Enter the virtual environment and Install related dependency packages:
```
conda activate agent
```
```
pip install -r ./requirements.txt
```
3. Install the BLIP model locally, open the [BLIP website](https://huggingface.co/Salesforce/blip-image-captioning-large), and download all files to ``Models/BLIP``.
4. Follow the prompts to configure the key for the API that needs to be used in the `.env`.
### **💻 2.2 Demo**
Multi Agent GPT provides UI interface interaction, allowing users to launch agents and achieve intelligent conversations by running the ``web.py``:
```
python ./web.py
```
The program will run a local URL: http://XXX. Open using a local browser to see the UI interface:
<div align="center">
</div>
### **📻 2.3 News**
#### 1 Chat_with_Image
By integrating the BLIP model, agents can understand image information and provide high-quality dialogue information.
## 🗄️ 3 Structure
```
- .env
- Agents/
- openai_agents.py #用来定义基于gpt3.5的agent
- Database/
- Docs/
- Imgs/
- Show/ #存储一些示例图片
- Models
- BLIP #图像理解大模型
- Tools/
- ImageCaption.py #基于BLIP的图像理解工具
- ImageGeneration.py #定义了一个基于openai dalle的文本生成图像的工具
- search.py #基于Google-search的联网搜索工具
- Utils/
- data_io.py
- stdio.py #实现了如何截获当前程序的日志信息，主要是用来获取agent的verbose信息
- utils_image.py #关于图像处理的一些功能函数
- utils_json.py #从已有的log日志信息中提取相关的有用字段(服务stdio)
- python_new_funciton.py #开发过程中的测试文件
- readme.md
- requirements.txt
- web.py #主运行文件
```Excerpt of 3,286 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f75bb96ff6b91249, name:multi-agent, desc:multi-agent, name:multi agent