Multi-Agent AI - Coding

Multi-Agent AI - Coding

A Gradio demo of several AI agents built with Microsoft AutoGen that work together on a coding task. Use it in the browser on Hugging Face or run a copy on your own computer.

Made by bstraehle on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Space is a Gradio demo of a multi-agent setup built with Microsoft AutoGen, aimed at coding. The agent logic lives in multi_agent.py and the page that you use is app.py. It runs in the browser on Hugging Face or on your own computer.

Who it suits: Developers who want to see a small AutoGen multi-agent example before building their own. Students of agent systems can read the two Python files to learn how the pieces connect.

Industry | Who uses it | How they use it | Example
Software | Developers | Try a multi-agent coding demo in a browser | Giving the agents a small coding task and reading what comes back
Education | Students of AI agents | Read how AutoGen agents are wired up | Opening multi_agent.py next to app.py
Research | Agent researchers | Use it as a small base to adapt | Copying the Space and changing the agent setup

If you want a full coding assistant inside your editor, you can skip it.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Windows with Python
• macOS with Python
• Linux with Python

Use case | Who | What they get back
Try a multi-agent coding demo | Developers | A result produced by several agents working together
Study an AutoGen example | Students | Two short Python files to read

How to set it up: Online use needs nothing. A copy on your own computer needs a little.

• Python on Windows, macOS or Linux
• The pip tool, to install the packages from requirements.txt
• Nothing at all if you use the Space online, since it runs in the browser

1. Install the Hugging Face hub package.
2. Download the Space's files into a local folder.
3. Move into that folder.
4. Install Gradio at the pinned version, then the packages from requirements.txt.
5. Start the app.

pip install -U huggingface_hub
hf download bstraehle/multi-agent-ai-autogen-coding --repo-type space --local-dir multi-agent-ai-autogen-coding
cd multi-agent-ai-autogen-coding
pip install gradio==5.31.0
pip install -r requirements.txt
python app.py

How to use it: Online, open the Space's page and use the app there. On your own computer, run this command from the project folder and open the page Gradio shows.

python app.py

Example: You open the app and give it a coding task. The AutoGen agents work on it together, and the app shows what they produce.

For newcomers and experts: If you are new to this, open the Space's page and try one small coding request. Nothing needs installing, and you see several agents share one job.

If you know the field, the repository is just four files, with the agent logic kept apart from the Gradio page. The source does not say which model service the agents call or how many agents run, so read multi_agent.py before you rely on it.

Open the Space or run app.py locally
You give the app a coding task
AutoGen agents work on it together
The app shows the result

Good to know: The source says little, so check what the agents produce yourself.

• License: Apache 2.0, as the Space's license line says
• Cost to run: none named, and the hosted copy uses cpu-basic hardware at Hugging Face. The source does not say whether a model key is needed
• Data it reaches: the source names no files or accounts. The page carries an MCP tag, but no MCP setup is described

On Hugging Face, 13 November 2026

• Likes: 39
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/bstraehle/multi-agent-ai-autogen-coding
• Files: https://huggingface.co/spaces/bstraehle/multi-agent-ai-autogen-coding/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.