https://github.com/autogluon/autogluon-assistant
ML Assistant for Competitive Machine Learning
https://github.com/autogluon/autogluon-assistant
automl data-science llms machine-learning
Last synced: about 2 months ago
JSON representation
ML Assistant for Competitive Machine Learning
- Host: GitHub
- URL: https://github.com/autogluon/autogluon-assistant
- Owner: autogluon
- License: apache-2.0
- Created: 2024-04-29T07:23:46.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2025-01-06T23:43:53.000Z (over 1 year ago)
- Last Synced: 2025-01-20T09:07:05.924Z (over 1 year ago)
- Topics: automl, data-science, llms, machine-learning
- Language: Python
- Homepage:
- Size: 1.8 MB
- Stars: 98
- Watchers: 7
- Forks: 12
- Open Issues: 14
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
Awesome Lists containing this project
- awesome-agentic-machine-learning - AutoGluon Assistant - agent system for end-to-end multimodal ML automation. Also known as MLZero. |  | (AutoML Agents)
README
# AutoGluon Assistant (aka MLZero)
[](https://pypi.org/project/autogluon.assistant/)
[](./LICENSE)
[](https://github.com/autogluon/autogluon-assistant/actions/workflows/continuous_integration.yml)
[](https://project-mlzero.github.io/)
> **Official implementation** of [MLZero: A Multi-Agent System for End-to-end Machine Learning Automation](https://arxiv.org/abs/2505.13941)
AutoGluon Assistant (aka MLZero) is a multi-agent system that automates end-to-end multimodal machine learning or deep learning workflows by transforming raw multimodal data into high-quality ML solutions with zero human intervention.
---
## 📰 Latest News
| Date | Update |
|------|--------|
| [2025-12-01] | 💬 **Chat Mode**: New conversational Q&A mode (`mlzero chat`) for getting ML guidance without code execution. |
| [2025-11-25] | 🔄 **Performance Enhancement Release** (Node-Based Manager + MCTS, inspired by [ML-Master](https://github.com/sjtu-sai-agents/ML-Master) and [AIDE](https://github.com/codestoryai/aide)): Core algorithm merged and available to try now! Docker container coming soon. |
| [2025-10-23] | ✨ **Accepted to NeurIPS 2025** as a poster presentation |
---
## 📚 Documentation
For detailed usage instructions and advanced options, please refer to our tutorials:
- [Quickstart](docs/tutorials/quickstart.md)
- [LLM Providers](docs/tutorials/llm_providers.md) - Using different AI providers (Bedrock, OpenAI, Anthropic, SageMaker)
- [Interfaces](docs/tutorials/interfaces.md) - Working with different interfaces (CLI, Python API, WebUI, MCP)
- [Configuration](docs/tutorials/configuration.md) - Customizing AutoGluon Assistant settings
- [Chat Mode](docs/tutorials/chat_mode.md) - Interactive Q&A without code execution
---
## 💾 Installation
Linux-only support at present.
*Note: If you don't have conda installed, follow conda's [official installation guide](https://www.anaconda.com/docs/getting-started/miniconda/install#linux-2) to install it.*
For the latest features, install from source:
```bash
pip install uv && uv pip install git+https://github.com/autogluon/autogluon-assistant.git
```
---
## 🚀 Quick Start
MLZero supports multiple LLM providers with AWS Bedrock as the default:
```bash
export AWS_DEFAULT_REGION=""
export AWS_ACCESS_KEY_ID=""
export AWS_SECRET_ACCESS_KEY=""
```
To run MLZero in CLI:
```bash
mlzero -i
```
---
## 🐳 Docker
**Security Note**: MLZero executes LLM-generated code during operation. While this generally works fine for common machine learning tasks, running inside a Docker container is recommended for security reasons, as it provides an extra layer of isolation from your host system.
Build the Docker image from the **project root**.
```bash
docker build --no-cache -t mlzero:latest .
```
The image contains two conda environments: `mlzero` for running MLZero, and `maab` for MAAB benchmarking.
> **Note:** Run this from the repository root directory, not the `maab/` folder, unless you specifically want to build for running `maab/aws_batch_submit.sh` to benchmark MAAB with AWS Batch.
> **Version Info:** Each build pulls the latest code from the GitHub `main` branch. To use a specific branch or tag, pass the `BRANCH` build argument:
> ```bash
> docker build --no-cache --build-arg BRANCH= -t mlzero:latest .
> ```
Run the container:
```bash
docker run -it --gpus all --shm-size=32g mlzero:latest
# test MLZero in the docker
mlzero -i /opt/autogluon-assistant/maab/example_dataset/abalone/training
```
---
## 🖥️ Interfaces
AutoGluon Assistant provides multiple interfaces:
### CLI
### Web UI
### MCP (Model Context Protocol)
---
## 📝 Citation
If you use Autogluon Assistant (MLZero) in your research, please cite our paper:
```bibtex
@misc{fang2025mlzeromultiagentendtoendmachine,
title={MLZero: A Multi-Agent System for End-to-end Machine Learning Automation},
author={Haoyang Fang and Boran Han and Nick Erickson and Xiyuan Zhang and Su Zhou and Anirudh Dagar and Jiani Zhang and Ali Caner Turkmen and Cuixiong Hu and Huzefa Rangwala and Ying Nian Wu and Bernie Wang and George Karypis},
year={2025},
eprint={2505.13941},
archivePrefix={arXiv},
primaryClass={cs.MA},
url={https://arxiv.org/abs/2505.13941},
}
```