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.
AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
| Date | Stars |
|---|---|
| 2026-07-31 | 1454 |
| 2026-08-03 | 1461 |
| 2026-08-06 | 1467 |
Today
+6 stars today
This week
— stars this week
This month
— stars this month
Momentum
24.0
growth rate 0.00%/day
<h1 align="center">AIDE ML — The Machine Learning Engineering Agent</h1> <p align="center"><em> LLM‑driven agent that writes, evaluates & improves machine‑learning code. </em></p> <p align="center"> <a href="https://pypi.org/project/aideml/"><img src="https://img.shields.io/pypi/v/aideml?label=PyPI&logo=pypi" alt="PyPI"></a> <a href="https://www.python.org/"><img src="https://img.shields.io/badge/Python-3.10%2B-blue" alt="Python 3.10+"></a> <a href="https://arxiv.org/abs/2502.13138"><img src="https://img.shields.io/badge/arXiv-2502.13138-b31b1b?logo=arxiv&logoColor=white" alt="arXiv paper"></a> <img src="https://img.shields.io/github/license/WecoAI/aideml?color=brightgreen" alt="MIT License"> <a href="https://pepy.tech/projects/aideml"><img src="https://static.pepy.tech/badge/aideml" alt="PyPI Downloads"></a>  </p> <p align="center"> <a href="https://docs.weco.ai/cli/getting-started?utm_source=aidemlrepo" target="_blank"><strong>Use in Production? Try Weco →</strong></a> </p> # What Is AIDE ML? **AIDE ML is the open‑source “reference build” of the AIDE algorithm**, a tree‑search agent that autonomously drafts, debugs and benchmarks code until a user‑defined metric is maximised (or minimised). It ships as a *research‑friendly* Python package with batteries‑included utilities (CLI, visualisation, config presets) so that academics and engineer‑researchers can **replicate the paper, test new ideas, or prototyping ML pipelines**.  | Layer | Description | Where to find it | | --- | --- | --- | | **AIDE *algorithm*** | LLM‑guided agentic tree search in the space of code. | Described in our [paper](https://arxiv.org/abs/2502.13138). | | **AIDE ML *repo* (this repo)** | Lean implementation for experimentation & extension. | `pip install aideml` | | **Weco *product*** | The platform generalizes AIDE's capabilities to broader code optimization scenarios, providing experiment tracking and enhanced user control. | [weco.ai](https://weco.ai?utm_source=aidemlrepo) | ### Who should use it? - **Agent‑architecture researchers** – swap in new search heuristics, evaluators or LLM back‑ends. - **ML Practitioners** – quickly build a high performance ML pipelines given a dataset. # Key Capabilities - **Natural‑language task specification** Point the agent at a dataset and describe *goal* + *metric* in plain English. No YAML grids or bespoke wrappers. `aide data_dir=… goal="Predict churn" eval="AUROC"` - **Iterative *agentic tree search*** Each python script becomes a node in a solution tree; LLM‑generated patches spawn children; metric feedback prunes and guides the search. OpenAI’s **[MLE‑Bench](https://arxiv.org/abs/2410.07095)** (75 Kaggle comps) found the tree‑search of AIDE wins **4 × more medals** than the best linear agent (OpenHands). <div align="center"> <img src="https://github.com/user-attachments/assets/a48aa65e-360d-4d91-b4ad-98b0fe2585d4" width="80%"> </div> <details> <summary>Utility features provided by this repo</summary> - **HTML visualiser** – inspect the full solution tree and code attached to each node. - **Streamlit UI** – prototype ML solution . - **Model‑neutral plumbing** – OpenAI, Anthropic, Gemini, or any local LLM that speaks the OpenAI API. </details> ## Featured Research built on/with AIDE | Institution | Paper / Project Name | Links | |-------------|----------------------|-------| | **OpenAI** | MLE-bench: Evaluating Machine-Learning Agents on Machine-Learning Engineering | [Paper](https://arxiv.org/abs/2410.07095), [GitHub](https://github.com/openai/mle-bench) | | **METR** | RE-Bench: Evaluating frontier AI R&D capabilities of language-model agents against human experts | [Paper](https://arxiv.org/abs/2411.15114), [GitHub](https://github.com/METR/RE-Bench) | | **Sakana AI** | The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search | [Paper](htt
Excerpt of 8,271 characters
Read on GitHub
Dex Hunter · @WecoAI
36
Zhengyao Jiang · University College London · United Kingdom
21
8
7
6
3
2
Nada Amin · Harvard University · United States
2
1
1
Giulio Starace · Paradigma · Italy
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c54ba86d95a2ae07, topic:ai-agents, topic:autonomous-agents, readme:agentic
matched fp:c54ba86d95a2ae07, topic:llm