Stars
Agentic AI workshop: from the agent loop to multi-agents
Official Implementation of the Paper "Let's Predict Sentence by Sentence"
Swift Package to implement a transformers-like API in Swift
State-of-the-art paired encoder and decoder models (17M-1B params)
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
SHARPIE: Shared Human-AI Reinforcement Learning Platform for Interactive Experiments
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.
Simple & Scalable Pretraining for Neural Architecture Research
[EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"
Phantom-Data: Towards a General Subject-Consistent Video Generation Dataset
Copilot Chat extension for VS Code
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
The official PyTorch implementation of Google's Gemma models
A collection of guides and examples for the Gemma open models from Google.
The fastest, lightest, and easiest-to-integrate AI gateway on the market. Fully open-sourced.
An open-source AI agent that brings the power of Gemini directly into your terminal.