Clean PyTorch implementations of imitation and reward learning algorithms

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Maia is a human-like neural network chess engine trained on millions of human games.

Maia-2 is a new human-like neural network chess engine trained on millions of human games.

A chess library for Python, with move generation and validation, PGN parsing and writing, Polyglot opening book reading, Gaviota tablebase probing, Syzygy tablebase probing, and UCI/XBoard engine c…

🤖🪝Interpretability with tensordict and torch hooks.

Stanford NLP Python library for understanding and improving PyTorch models via interventions

Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]

A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗

React Flow | Svelte Flow - Powerful open source libraries for building node-based UIs with React (https://reactflow.dev) or Svelte (https://svelteflow.dev). Ready out-of-the-box and infinitely cust…

Instant AI code reviews

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

Build Conversational AI in minutes ⚡️

Python library for Agentic Document Extraction from LandingAI

React Hooks for Data Fetching

🤖 Just a command runner

Scalar is an open-source API platform:　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　🌐 Modern Rest API Client　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　📖 Beautiful API References　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　…

A Payload CMS plugin for OpenAPI (3.0, 3.1) specification generation

A collection of MARL benchmarks based on TorchRL

This component allows you to wrap your entire React application or each component in an <iframe>.

MOISE+MARL is an organizationally-guided framework designed to enhance control and explainability in Multi-Agent Reinforcement Learning (MARL) by structuring agents' behaviors through predefined ro…

Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors

A reusable framework for successor features for transfer in deep reinforcement learning using keras.

An extremely fast Python type checker and language server, written in Rust.

Modern open-source time-tracking app

An open protocol enabling communication and interoperability between opaque agentic applications.