🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

The absolute trainer to light up AI agents.

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

verl: Volcano Engine Reinforcement Learning for LLMs

Umami is a modern, privacy-focused alternative to Google Analytics.

MCP Toolbox for Databases is an open source MCP server for databases.

Visual Studio Code

(ICLR 2025) TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling

Deep Critical Research Agent : The first AI-driven Critical Analysis to turn the huge amount of preclinical biology data and information into knowledge and hence disease cures.

Lightweight coding agent that runs in your terminal

PNDbotics model files (urdf/mjcf + meshes, etc)

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

A PyTorch native platform for training generative AI models

Python binding for curl-impersonate fork via cffi. A http client that can impersonate browser tls/ja3/http2 fingerprints.

Build Real-Time Knowledge Graphs for AI Agents

An interface library for RL post training with environments.

Tongyi Deep Research, the Leading Open-source Deep Research Agent

The leading data integration platform for ETL / ELT data pipelines from APIs, databases & files to data warehouses, data lakes & data lakehouses. Both self-hosted and Cloud-hosted.

Check your ranking in GitHub! Don't forget to star ⭐ this repository.

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

The Database Toolkit for Python

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

The LLM Evaluation Framework

Full stack, modern web application template. Using FastAPI, React, SQLModel, PostgreSQL, Docker, GitHub Actions, automatic HTTPS and more.

Tooling support for the Polylith Architecture in Python.

Example Polylith setup for Python and uv

Suite of motion imitation methods for training controllers.