{"id":24445159,"url":"https://github.com/autogluon/autogluon-assistant","last_synced_at":"2026-04-01T20:31:50.780Z","repository":{"id":263790743,"uuid":"793416920","full_name":"autogluon/autogluon-assistant","owner":"autogluon","description":"ML Assistant for Competitive Machine Learning","archived":false,"fork":false,"pushed_at":"2025-01-06T23:43:53.000Z","size":1890,"stargazers_count":98,"open_issues_count":14,"forks_count":12,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-01-20T09:07:05.924Z","etag":null,"topics":["automl","data-science","llms","machine-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/autogluon.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-04-29T07:23:46.000Z","updated_at":"2025-01-16T04:32:58.000Z","dependencies_parsed_at":"2024-12-19T19:22:25.368Z","dependency_job_id":"58365c35-6df0-4027-bc54-9ba5d4ee5a3d","html_url":"https://github.com/autogluon/autogluon-assistant","commit_stats":null,"previous_names":["autogluon/autogluon-assistant"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autogluon%2Fautogluon-assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autogluon%2Fautogluon-assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autogluon%2Fautogluon-assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autogluon%2Fautogluon-assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/autogluon","download_url":"https://codeload.github.com/autogluon/autogluon-assistant/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":235519884,"owners_count":19003201,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["automl","data-science","llms","machine-learning"],"created_at":"2025-01-20T23:17:16.225Z","updated_at":"2026-04-01T20:31:50.773Z","avatar_url":"https://github.com/autogluon.png","language":"Python","funding_links":[],"categories":["AutoML Agents"],"sub_categories":[],"readme":"\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"70%\"\u003e\n\n# AutoGluon Assistant (aka MLZero)\n\n[![Python Versions](https://img.shields.io/badge/python-3.10%20|%203.11%20|%203.12-blue)](https://pypi.org/project/autogluon.assistant/)\n[![GitHub license](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](./LICENSE)\n[![Continuous Integration](https://github.com/autogluon/autogluon-assistant/actions/workflows/continuous_integration.yml/badge.svg)](https://github.com/autogluon/autogluon-assistant/actions/workflows/continuous_integration.yml)\n[![Project Page](https://img.shields.io/badge/Project_Page-MLZero-blue)](https://project-mlzero.github.io/)\n\n\u003c/td\u003e\n\u003ctd\u003e\n\u003cimg src=\"https://user-images.githubusercontent.com/16392542/77208906-224aa500-6aba-11ea-96bd-e81806074030.png\" width=\"350\"\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n\u003e **Official implementation** of [MLZero: A Multi-Agent System for End-to-end Machine Learning Automation](https://arxiv.org/abs/2505.13941)\n\nAutoGluon 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.\n\n---\n\n## 📰 Latest News\n\n| Date | Update |\n|------|--------|\n| [2025-12-01] | 💬 **Chat Mode**: New conversational Q\u0026A mode (`mlzero chat`) for getting ML guidance without code execution. |\n| [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. |\n| [2025-10-23] | ✨ **Accepted to NeurIPS 2025** as a poster presentation |\n\n---\n\n## 📚 Documentation\n\nFor detailed usage instructions and advanced options, please refer to our tutorials:\n\n- [Quickstart](docs/tutorials/quickstart.md)\n- [LLM Providers](docs/tutorials/llm_providers.md) - Using different AI providers (Bedrock, OpenAI, Anthropic, SageMaker)\n- [Interfaces](docs/tutorials/interfaces.md) - Working with different interfaces (CLI, Python API, WebUI, MCP)\n- [Configuration](docs/tutorials/configuration.md) - Customizing AutoGluon Assistant settings\n- [Chat Mode](docs/tutorials/chat_mode.md) - Interactive Q\u0026A without code execution\n\n---\n\n## 💾 Installation\n\nLinux-only support at present.\n\n*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.*\n\nFor the latest features, install from source:\n\n```bash\npip install uv \u0026\u0026 uv pip install git+https://github.com/autogluon/autogluon-assistant.git\n```\n\n---\n\n## 🚀 Quick Start\n\nMLZero supports multiple LLM providers with AWS Bedrock as the default:\n\n```bash\nexport AWS_DEFAULT_REGION=\"\u003cyour-region\u003e\"\nexport AWS_ACCESS_KEY_ID=\"\u003cyour-access-key\u003e\"\nexport AWS_SECRET_ACCESS_KEY=\"\u003cyour-secret-key\u003e\"\n```\n\nTo run MLZero in CLI:\n\n```bash\nmlzero -i \u003cinput_data_folder\u003e\n```\n\n---\n\n## 🐳 Docker\n\n**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.\n\nBuild the Docker image from the **project root**.\n\n```bash\ndocker build --no-cache -t mlzero:latest .\n```\n\nThe image contains two conda environments: `mlzero` for running MLZero, and `maab` for MAAB benchmarking.\n\n\u003e **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.\n\n\u003e **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:\n\u003e ```bash\n\u003e docker build --no-cache --build-arg BRANCH=\u003cbranch-or-tag\u003e -t mlzero:latest .\n\u003e ```\n\nRun the container:\n\n```bash\ndocker run -it --gpus all --shm-size=32g mlzero:latest\n# test MLZero in the docker\nmlzero -i /opt/autogluon-assistant/maab/example_dataset/abalone/training\n```\n\n---\n\n## 🖥️ Interfaces\n\nAutoGluon Assistant provides multiple interfaces:\n\n### CLI\n\n![Demo](https://github.com/autogluon/autogluon-assistant/blob/main/docs/assets/cli_demo.gif)\n\n### Web UI\n\n![Demo](https://github.com/autogluon/autogluon-assistant/blob/main/docs/assets/web_demo.gif)\n\n### MCP (Model Context Protocol)\n\n![Demo](https://github.com/autogluon/autogluon-assistant/blob/main/docs/assets/mcp_demo.gif)\n\n---\n\n## 📝 Citation\n\nIf you use Autogluon Assistant (MLZero) in your research, please cite our paper:\n\n```bibtex\n@misc{fang2025mlzeromultiagentendtoendmachine,\n      title={MLZero: A Multi-Agent System for End-to-end Machine Learning Automation}, \n      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},\n      year={2025},\n      eprint={2505.13941},\n      archivePrefix={arXiv},\n      primaryClass={cs.MA},\n      url={https://arxiv.org/abs/2505.13941}, \n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fautogluon%2Fautogluon-assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fautogluon%2Fautogluon-assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fautogluon%2Fautogluon-assistant/lists"}