<div align="center">
<h1 align="center">MLE-Agent: Your intelligent companion for seamless AI engineering and research.</h1>
<img alt="kaia-llama" height="200px" src="assets/kaia_llama.webp">
<a href="https://trendshift.io/repositories/11658" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11658" alt="MLSysOps%2FMLE-agent | Trendshift" style="width: 250px; height: 200px;" width="250" height="200px"/></a>
<p align="center">:love_letter: Fathers' love for Kaia :love_letter:</p>
[](https://pepy.tech/project/mle-agent)
<a href="https://discord.gg/SgxBpENGRG"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=flat" alt="Join our Discord community"></a>
[📚 Docs](https://mle-agent-site.vercel.app/) |
[🐞 Report Issues](https://github.com/MLSysOps/MLE-agent/issues/new) |
👋 Join us on <a href="https://discord.gg/SgxBpENGRG" target="_blank">Discord</a>
</div>
## Overview
MLE-Agent is designed as a pairing LLM agent for machine learning engineers and researchers. It is featured by:
- 🤖 Autonomous Baseline Creation: Automatically builds ML/AI baselines.
- 🔍 [Arxiv](https://arxiv.org/) and [Papers with Code](https://paperswithcode.com/) Integration: Access best practices and state-of-the-art methods.
- 🐛 Smart Debugging: Ensures high-quality code through automatic debugger-coder interactions.
- 📂 File System Integration: Organizes your project structure efficiently.
- 🧰 Comprehensive Tools Integration: Includes AI/ML functions and MLOps tools for a seamless workflow.
- ☕ Interactive CLI Chat: Enhances your projects with an easy-to-use chat interface.
- 📊 Weekly Report: Automatically generates detailed summaries of your weekly works.
https://github.com/user-attachments/assets/dac7be90-c662-4d0d-8d3a-2bc4df9cffb9
## Milestones
- :rocket: 09/10/2024: Release the `0.4.0` with new CLIs like `MLE report`, `MLE kaggle`, `MLE integration` and many new models like `Mistral`.
- :rocket: 07/25/2024: Release the `0.3.0` with huge refactoring, many integrations, etc (v0.3.0)
- :rocket: 07/11/2024: Release the `0.2.0` with multiple agents interaction (v0.2.0)
- 👨🍼 **07/03/2024: Kaia is born**
- :rocket: 06/01/2024: Release the first rule-based version of MLE agent (v0.1.0)
## Get started
### Installation
```bash
pip install mle-agent -U
# or from source
git clone git@github.com:MLSysOps/MLE-agent.git
pip install -e .
```
### Usage
```bash
mle new <project name>
```
And a project directory will be created under the current path, you need to start the project under the project directory.
```bash
cd <project name>
mle start
```
You can also start an interactive chat in the terminal under the project directory:
```bash
mle chat
```
## Use cases
### :bar_chart: Generate Work Report
MLE agent can help you summarize your weekly report, including development progress, communication notes, and to-do lists.
```bash
cd <project name>
mle report
```
Then, you can visit http://localhost:3000/ to generate your report locally.
### :trophy: Start with Kaggle Competition
MLE agent can participate in Kaggle competitions and finish coding and debugging from data preparation to model training independently.
For more details, see the [MLE-Agent Tutorials](https://mle-agent-site.vercel.app/tutorial/Start_a_kaggle_task).
```bash
cd <project name>
mle kaggle
```
## Roadmap
The following is a list of the tasks we plan to do, welcome to propose something new!
<details>
<summary><b> :hammer: General Features</b></summary>
- [x] Understand users' requirements to create an end-to-end AI project
- [x] Suggest the SOTA data science solutions by using the web search
- [x] Plan the ML engineering tasks with human interaction
- [x] Execute the code on the local machine/cloud, debug and fix the errors
- [x] Leverage the built-in functions to complete ML engineering tasks
- [x] Interactive chat: A human-in-the-loop mode to help improve the existing ML projects
- [x] Kaggle mode: to finish a Kaggle task without humans
- [ ] Summary and reflect the whole ML/AI pipeline
- [ ] Integration with Cloud data and testing and debugging platforms
- [x] Local RAG support to make personal ML/AI coding assistant
- [ ] Function zoo: generate AI/ML functions and save them for future usage
</details>
<details>
<summary><b>:star: More LLMs and Serving Tools</b></summary>
- [x] Ollama LLama3
- [x] OpenAI GPTs
- [x] Anthropic Claude 3.5 Sonnet
</details>
<details>
<summary><b>:sparkling_heart: Better user experience</b></summary>
- [x] CLI Application
- [x] Web UI
- [x] Discord
</details>
<details>
<summary><b>:jigsaw: Functions and Integrations</b></summary>
- [x] Local file system
- [x] Local code exectutor
- [x] Arxiv.org search
- [x] Papers with Code search
- [x] General keyword search
- [ ] Hugging Face
- [ ] SkyPilot cloud deployment
- [ ] Snowflake data
- [ ] AWS S3 data
- [ ] Databricks data catalog
- [ ] Wandb experiment monitoring
- [ ] MLflow management
- [ ] DBT data transform
</details>
</details>
## Contributing
We welcome contributions from the community. We are looking for contributors to help us with the following tasks:
- Benchmark and Evaluate the agent
- Add more features to the agent
- Improve the documentation
- Write tests
Please check the [CONTRIBUTING.md](CONTRIBUTING.md) file if you want to contribute.
## Support and Community
- [Discord community](https://discord.gg/SgxBpENGRG). If you have any questions, please ask in the Discord community.
## Star History
[](https://star-history.com/#MLSysOps/MLE-agent&Date)
## License
Check [MIT License](LICENSE) file for more information.
Raw data
{
"_id": null,
"home_page": "https://github.com/MLSysOps/MLE-agent",
"name": "mle-agent",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "LLM, deep learning, MLOps, shell, neural networks",
"author": "Yizheng Huang, Huaizheng Zhang",
"author_email": "huangyz0918@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/13/cf/59fa53308cced9caaac6c9128fe4eeb9baff338d949334172d265d8328ba/mle_agent-0.4.2.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n<h1 align=\"center\">MLE-Agent: Your intelligent companion for seamless AI engineering and research.</h1>\n<img alt=\"kaia-llama\" height=\"200px\" src=\"assets/kaia_llama.webp\">\n<a href=\"https://trendshift.io/repositories/11658\" target=\"_blank\"><img src=\"https://trendshift.io/api/badge/repositories/11658\" alt=\"MLSysOps%2FMLE-agent | Trendshift\" style=\"width: 250px; height: 200px;\" width=\"250\" height=\"200px\"/></a>\n<p align=\"center\">:love_letter: Fathers' love for Kaia :love_letter:</p>\n\n \n \n\n[](https://pepy.tech/project/mle-agent)\n\n<a href=\"https://discord.gg/SgxBpENGRG\"><img src=\"https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=flat\" alt=\"Join our Discord community\"></a>\n\n[\ud83d\udcda Docs](https://mle-agent-site.vercel.app/) | \n[\ud83d\udc1e Report Issues](https://github.com/MLSysOps/MLE-agent/issues/new) | \n\ud83d\udc4b Join us on <a href=\"https://discord.gg/SgxBpENGRG\" target=\"_blank\">Discord</a>\n\n</div>\n\n\n## Overview\n\nMLE-Agent is designed as a pairing LLM agent for machine learning engineers and researchers. It is featured by:\n\n- \ud83e\udd16 Autonomous Baseline Creation: Automatically builds ML/AI baselines.\n- \ud83d\udd0d [Arxiv](https://arxiv.org/) and [Papers with Code](https://paperswithcode.com/) Integration: Access best practices and state-of-the-art methods.\n- \ud83d\udc1b Smart Debugging: Ensures high-quality code through automatic debugger-coder interactions.\n- \ud83d\udcc2 File System Integration: Organizes your project structure efficiently.\n- \ud83e\uddf0 Comprehensive Tools Integration: Includes AI/ML functions and MLOps tools for a seamless workflow.\n- \u2615 Interactive CLI Chat: Enhances your projects with an easy-to-use chat interface.\n- \ud83d\udcca Weekly Report: Automatically generates detailed summaries of your weekly works.\n\n\nhttps://github.com/user-attachments/assets/dac7be90-c662-4d0d-8d3a-2bc4df9cffb9\n\n## Milestones\n\n- :rocket: 09/10/2024: Release the `0.4.0` with new CLIs like `MLE report`, `MLE kaggle`, `MLE integration` and many new models like `Mistral`.\n- :rocket: 07/25/2024: Release the `0.3.0` with huge refactoring, many integrations, etc (v0.3.0)\n- :rocket: 07/11/2024: Release the `0.2.0` with multiple agents interaction (v0.2.0)\n- \ud83d\udc68\u200d\ud83c\udf7c **07/03/2024: Kaia is born**\n- :rocket: 06/01/2024: Release the first rule-based version of MLE agent (v0.1.0)\n\n## Get started\n\n### Installation\n\n```bash\npip install mle-agent -U\n# or from source\ngit clone git@github.com:MLSysOps/MLE-agent.git\npip install -e .\n```\n\n### Usage\n\n```bash\nmle new <project name>\n```\n\nAnd a project directory will be created under the current path, you need to start the project under the project directory.\n\n```bash\ncd <project name>\nmle start\n```\n\nYou can also start an interactive chat in the terminal under the project directory:\n\n```bash\nmle chat\n```\n\n## Use cases\n\n### :bar_chart: Generate Work Report\n\nMLE agent can help you summarize your weekly report, including development progress, communication notes, and to-do lists.\n\n```bash\ncd <project name>\nmle report\n```\nThen, you can visit http://localhost:3000/ to generate your report locally.\n\n### :trophy: Start with Kaggle Competition\n\nMLE agent can participate in Kaggle competitions and finish coding and debugging from data preparation to model training independently.\nFor more details, see the [MLE-Agent Tutorials](https://mle-agent-site.vercel.app/tutorial/Start_a_kaggle_task).\n\n```bash\ncd <project name>\nmle kaggle\n```\n\n## Roadmap\n\nThe following is a list of the tasks we plan to do, welcome to propose something new!\n\n<details>\n <summary><b> :hammer: General Features</b></summary>\n \n - [x] Understand users' requirements to create an end-to-end AI project\n - [x] Suggest the SOTA data science solutions by using the web search\n - [x] Plan the ML engineering tasks with human interaction\n - [x] Execute the code on the local machine/cloud, debug and fix the errors\n - [x] Leverage the built-in functions to complete ML engineering tasks\n - [x] Interactive chat: A human-in-the-loop mode to help improve the existing ML projects\n - [x] Kaggle mode: to finish a Kaggle task without humans\n - [ ] Summary and reflect the whole ML/AI pipeline\n - [ ] Integration with Cloud data and testing and debugging platforms\n - [x] Local RAG support to make personal ML/AI coding assistant\n - [ ] Function zoo: generate AI/ML functions and save them for future usage\n\n\n</details>\n\n<details>\n <summary><b>:star: More LLMs and Serving Tools</b></summary>\n \n - [x] Ollama LLama3\n - [x] OpenAI GPTs\n - [x] Anthropic Claude 3.5 Sonnet\n</details>\n\n<details>\n <summary><b>:sparkling_heart: Better user experience</b></summary>\n\n - [x] CLI Application\n - [x] Web UI\n - [x] Discord\n</details>\n\n<details>\n <summary><b>:jigsaw: Functions and Integrations</b></summary>\n \n - [x] Local file system\n - [x] Local code exectutor\n - [x] Arxiv.org search\n - [x] Papers with Code search\n - [x] General keyword search\n - [ ] Hugging Face\n - [ ] SkyPilot cloud deployment\n - [ ] Snowflake data\n - [ ] AWS S3 data\n - [ ] Databricks data catalog\n - [ ] Wandb experiment monitoring\n - [ ] MLflow management\n - [ ] DBT data transform\n</details>\n\n</details>\n\n## Contributing\n\nWe welcome contributions from the community. We are looking for contributors to help us with the following tasks:\n\n- Benchmark and Evaluate the agent\n- Add more features to the agent\n- Improve the documentation\n- Write tests\n\nPlease check the [CONTRIBUTING.md](CONTRIBUTING.md) file if you want to contribute.\n\n## Support and Community\n\n- [Discord community](https://discord.gg/SgxBpENGRG). If you have any questions, please ask in the Discord community.\n\n## Star History\n\n[](https://star-history.com/#MLSysOps/MLE-agent&Date)\n\n## License\n\nCheck [MIT License](LICENSE) file for more information.\n",
"bugtrack_url": null,
"license": null,
"summary": "MLE-agent: An agent to automate your MLE processes",
"version": "0.4.2",
"project_urls": {
"Download": "https://github.com/MLSysOps/MLE-agent/archive/refs/heads/main.zip",
"Homepage": "https://github.com/MLSysOps/MLE-agent"
},
"split_keywords": [
"llm",
" deep learning",
" mlops",
" shell",
" neural networks"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "eb19116aa723d8133af8fadd3c302e2226f7f61d85f3386a0dd77eb00d11bf51",
"md5": "3b0fbef16efaa8b99ad2e963610256c6",
"sha256": "d3e962440ec789c7ca3acf45cb0d4ab866616445738a8decf4a4919155df2c19"
},
"downloads": -1,
"filename": "mle_agent-0.4.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "3b0fbef16efaa8b99ad2e963610256c6",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 65705,
"upload_time": "2024-10-12T16:46:13",
"upload_time_iso_8601": "2024-10-12T16:46:13.683348Z",
"url": "https://files.pythonhosted.org/packages/eb/19/116aa723d8133af8fadd3c302e2226f7f61d85f3386a0dd77eb00d11bf51/mle_agent-0.4.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "13cf59fa53308cced9caaac6c9128fe4eeb9baff338d949334172d265d8328ba",
"md5": "badf27b45341f19f299d6351d9f81075",
"sha256": "440c60701826f428962cea563b2d1d1f4c05cca86818b0496c00b6ca5229faa8"
},
"downloads": -1,
"filename": "mle_agent-0.4.2.tar.gz",
"has_sig": false,
"md5_digest": "badf27b45341f19f299d6351d9f81075",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 354452,
"upload_time": "2024-10-12T16:46:15",
"upload_time_iso_8601": "2024-10-12T16:46:15.244946Z",
"url": "https://files.pythonhosted.org/packages/13/cf/59fa53308cced9caaac6c9128fe4eeb9baff338d949334172d265d8328ba/mle_agent-0.4.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-12 16:46:15",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "MLSysOps",
"github_project": "MLE-agent",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "mle-agent"
}
JSON
