Trending Projects

A private AI platform for building agents, assistants, and enterprise search with multi-model support and API connectivity.

FaceSwap for deep learning face swapping in media

A tensor library for machine learning, with a focus on large language models and automatic differentiation.

Llama 2 inference code for running Llama models

Continuously updated machine learning and deep learning notes and demos by a dedicated researcher.

Comprehensive learning roadmap for AI & machine learning, with 200+ practical cases and projects for beginners to experts.

TypeScript/JavaScript SDK for Gemini and Vertex AI, enabling developers to build AI-powered applications.

A curated collection of resources for machine learning, deep learning, and distributed systems development.

Easily run, manage, and scale AI workloads on any infrastructure using a unified platform.

A Python-based tool that generates high-fidelity 3D assets from images with production-ready PBR materials.

Demystify AI agents by building them yourself with no black boxes, real understanding of function calling, memory, and ReAct patterns.

Zero-shot voice conversion and singing voice conversion library with real-time support for vibe coders.

AI Crash Course to help busy builders catch up to the public frontier of AI research in 2 weeks

An open-source guide for building a 'Tiny-Universe' of large language models and AI tools.

A LangChain-based framework for end-to-end natural language to data insight conversion, with MCP Skills multi-agent architecture.

Kortix is a platform for building and managing autonomous AI agents with capabilities in browser automation, file management, and system operations.

A comprehensive benchmark for evaluating the capabilities of Chinese large language models (LLMs)

Mooncake is a serving platform for Kimi, a leading LLM service provided by Moonshot AI, focused on disaggregation, inference, and RDMA.

A curated reading list for security, safety, and privacy of large language models (LLMs) and AI systems.

A modern, cross-platform, and free AI RSS reader built with Go.

A comprehensive collection of resources and tutorials for building AI infrastructure and systems.

CodeGeeX4 is a versatile AI model for code completion, interpretation, web search, and more for software development.

A library for generating 3D models using compact, structured latent representations.

Deep learning tuning playbook for maximizing model performance

Latitude is an open-source platform for building, evaluating, and refining prompts for large language models.

A block-style editor with clean JSON output for vibe coders

Kimi-Audio is an open-source audio foundation model for understanding, generating, and conversing with audio.

High-performance Node.js image processing library for resizing and converting images quickly

Dispatcharr is a Python-based platform for building and deploying AI-powered applications and services.

Sealos is an AI-native Cloud Operating System that unifies the entire application lifecycle for building and scaling modern AI applications.

Utilities for working with Llama language models, a type of large language model.

A production-ready FastAPI template for building scalable, secure, and maintainable AI agent services with LangGraph integration.

PyTorch Lightning simplifies deep learning training and deployment at scale.

An AI-powered GitHub Action that analyzes code changes for security vulnerabilities using the Claude language model.

This GitHub repository contains code for reproducing large language model (LLM) related algorithms and learning materials.

A comprehensive AI Red Teaming platform for security researchers and developers.

A fast and versatile tool for recording, slicing, and rendering Bilibili live streams with integrated ML models.

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

DeepEP is an efficient expert-parallel communication library for CUDA-based applications.

Optuna is a hyperparameter optimization framework that enables efficient and scalable model tuning for machine learning.

CUDA Python: A library that brings the power of CUDA to Python, enabling high-performance GPU acceleration.

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

A distributed inference serving framework for AI applications, built with Rust for high performance and scalability.

An open-source, GPU-accelerated physics simulation engine for roboticists and simulation researchers.

Real-time multi-person keypoint detection for body, face, hands, and foot

CVAT is an industry-leading data engine for machine learning, trusted by teams for annotating data at scale.

LocalGPT enables private document interaction with GPT models on your device.

Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser

An open-source browser extension that provides immersive translation capabilities for developers working with AI tools.

OpenVINO is an open-source toolkit for optimizing and deploying AI inference on a variety of hardware.