Trending Projects

A high-performance 3D rendering library for ray tracing and hybrid rasterization of Gaussian particles.

An AI-powered framework to evaluate the safety and alignment of large language models.

A TypeScript library for building AI-powered workflows and applications using LangChain.

Open-source Grok-1 model for local inference with JAX

A general-purpose programming language repository for developers interested in AI tools and applications.

Tools for merging and optimizing large language models for AI applications.

This project aims to speed up large language model (LLM) inference and enhance their understanding of key information through prompt and KV-Cache compression.

An AI observability platform for production LLM and agent systems, built with Python and Pydantic.

A GitHub repository for a developer discovery platform focused on 'vibe coders' (developers who build with AI tools).

LLM model optimized for coding tasks and autonomous agent workflows

Manifold is a C++ geometry library focused on topological robustness for AI-powered applications.

A Foundation Model for Generalist Gaming Agents, a powerful AI framework for building versatile gaming agents.

A personal memory system to power AI apps, built with a modern tech stack including TypeScript, Remix, and Prisma.

An async RL training library for scaling AI model training and deployment.

Generates neural network diagrams in LaTeX for reports and presentations

A collection of figures and templates for improving scientific writing with machine learning.

Open-source code for AlphaFold 2, a powerful AI system for predicting protein structures.

An open-source, large language model-based multimodal dialogue system that achieves near-GPT-4o performance.

Open source real-time translation app for Android that runs locally using AI models.

ModelScope is an open-source AI framework that brings the notion of Model-as-a-Service to life, providing a comprehensive suite of tools for building, deploying, and managing AI models.

A collection of prompts, workflows, and tools for agentic engineering with AI tools and language models.

A high-performance compute language extension for Rust that enables GPU acceleration and CUDA support.

LocalAGI is a self-hostable AI agent platform focused on privacy and flexibility, with advanced capabilities for consumer-grade hardware.

AI learning repository with tutorials and implementations for machine learning, deep learning, and data analysis

Recommenders is a project for prototyping and operationalizing recommendation systems with Jupyter notebooks and best practices.

Open-source machine learning compiler framework for building and optimizing AI models across a variety of hardware.

Python bindings for the llama.cpp library, enabling developers to use LLMs in their Python projects.

A collection of pre-trained, state-of-the-art AI models in the ONNX format for developers to use in their projects.

A lightweight LMM-based Document Parsing Model for developers working with AI tools.

A nearly-live implementation of OpenAI's Whisper, a powerful speech recognition and translation tool.

A Python tool that uses GPT-4, FFmpeg, and OpenCV to automatically analyze videos, extract the most interesting sections, and crop them for an improved viewing experience.

GVHMR is a Jupyter Notebook project for recovering human motion via gravity-view coordinates.

A GPT-SoVITS ONNX Inference Engine & Model Converter to enable voice cloning and text-to-speech for developers.

AgentQL is a suite of tools for connecting your AI to the web, featuring a query language and Playwright integrations for web automation and data extraction.

Repository of code samples for the book 'Neural Networks and Deep Learning' focused on machine learning.

Unified, production-ready inference API to run open-source, speech, and multimodal models on cloud, on-prem, or your laptop.

The Havoc Framework is a Go-based framework for building AI-powered applications and tools.

Experimental AI framework for automating video content creation on platforms like YouTube Shorts and TikTok.

Modeling, training, evaluation, and inference code for OLMo, a large language model.

Mesa is an open-source Python library for agent-based modeling and simulation of complex systems.

A library for developing neural operators using Fourier methods and PyTorch, enabling efficient learning on infinite dimensional spaces.

An open-ended evolution system for self-improving AI agents that can be used for developing advanced AI applications.

A Python library for building generative social simulations with multi-agent interactions.

Deep learning library for fast and easy model building

GPT-2 language model code and research from OpenAI

Rasa is an open-source framework for building conversational AI agents with NLU and dialogue management.

Bullet Physics SDK is a real-time collision detection and multi-physics simulation library for VR, games, robotics and more.

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

This repo is an experiment where ChatGPT manages a real-money micro-cap stock portfolio.

An annotated implementation of the Transformer paper, a key deep learning model for NLP tasks.