Trending Projects

A minimal TypeScript plugin that allows developers using the Claude AI assistant to receive phone calls.

Python ETL framework for real-time analytics and LLM pipelines

AIOS is an AI agent operating system that enables developers to build AI-powered applications and tools.

Unstructured is an open-source ETL solution for transforming complex documents into structured data for language models.

A collection of sample agents built with the Agent Development Kit (ADK) for building AI-powered applications.

An open-source Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

State-of-the-art diffusion models for image, audio, and video generation in PyTorch.

A reverse-engineered Python API for interacting with the Google Gemini web app, a generative AI tool.

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

A community-driven platform that transforms study materials into interactive resources like quizzes, flashcards, notes, and podcasts.

A comprehensive Python library for quantitative trading strategies, including indicators, pattern recognition, and portfolio optimization.

Open-source self-hosted sandboxes for AI agents, enabling secure and scalable AI development.

An autonomous agent framework for building AI-powered chatbots, plugins, and applications across various platforms.

LeetCUDA is a comprehensive collection of modern CUDA learning resources, including 200+ CUDA kernels, Tensor Cores, HGEMM, and FA-2 MMA.

The LLM vulnerability scanner, a Python-based tool for identifying security vulnerabilities in large language models.

This repository provides the Chinese Simplified documentation for the TVM (Tensor Virtual Machine) framework, a popular open-source deep learning compiler stack.

Autonomous red team framework automating offensive security ops with AI agents

Python robotics algorithms and textbook for developers.

2D/3D face analysis with AI

Real-time AI assistant for Ray-Ban smart glasses using vision, voice, and agentic actions via Gemini Live.

A framework for few-shot evaluation of language models, useful for vibe coders working with AI tools.

Code for machine learning-based algorithmic trading strategies and workflows.

Wan is an open-source, advanced large-scale video generative model for developers building AI-powered video applications.

An open platform for managing, monitoring, and optimizing large language models (LLMs) and AI workflows.

Frontier CoreML audio models for iOS and macOS apps with text-to-speech, speech-to-text, voice activity detection, and speaker diarization.

A flexible framework for optimizing heterogeneous LLM inference and fine-tuning workflows.

Moshi is an open-source speech-to-text foundation model and dialogue framework for building AI-powered voice apps.

A PyTorch-based reference implementation and models for the DINOv3 self-supervised vision transformer.

An AI-powered tool for removing hard-coded subtitles and text-like watermarks from videos or pictures, with no need for third-party APIs.

Production-ready templates to quickly ship AI agents to Google Cloud with built-in CI/CD, evaluation, and observability.

Deep learning paper implementations with side-by-side notes and explanations

A Python SDK for building AI agents with a model-driven approach in just a few lines of code.

A Flutter-based LLM chat client with support for mobile and desktop platforms.

CLIP is a neural network for zero-shot image-text matching and understanding

An AI-powered video note-taking tool that generates notes and summaries for your videos

Open-source platform for building enterprise-grade agents with RAG, workflows, and MCP tools

Effortless data labeling with AI support from Segment Anything and other powerful models.

NarratoAI is a Python-based tool that uses AI models to automatically provide commentary and edit videos with a single click.

Sample code and notebooks for using Generative AI on Google Cloud, with Gemini on Vertex AI.

FinRL is a financial reinforcement learning library that helps developers build AI-driven trading agents.

LLM入门教程，基于吴恩达课程的中文版实践指南

A Python library for serving large language models (LLMs) with high performance, including GPU acceleration and distributed inference.

Generates natural speech for dialogue scenarios

AI-powered photo management and organization with self-hosting capabilities

Flux 2 is a pure C inference engine for an image generation model, useful for vibe coders working with AI tools.

WorldGen is a Python library that can generate any 3D scene in seconds using AI and computer graphics techniques.

JAX is a high-performance numerical computing library for Python, enabling transformations like differentiation and JIT compilation for GPUs/TPUs.

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

A Python library that allows developers to use Microsoft Edge's online text-to-speech service without requiring Edge or an API key.

Lightweight AI assistant with cross-platform support for Claude, GPT, and Gemini