Trending Projects

Agent Zero is an AI framework for building autonomous AI agents and assistants in Python.

A comprehensive guide to large language models (LLMs) for developers, covering interview prep, knowledge sharing, and more.

A repository for running inference with the Meta Segment Anything Model 2 (SAM 2) and example notebooks.

WeChat message archiver with AI integration

This Python library provides a preview of computer usage data, potentially useful for AI coding tools.

A comprehensive collection of resources for large language models, including AI coding tools, MCP frameworks, and more.

A Python library for building AI-powered applications and integrating with large language models.

A PyTorch library for Bayesian optimization, a powerful tool for machine learning model tuning and optimization.

A Python library that translates videos from one language to another, with support for dubbing and subtitles.

End-to-end tutorials covering production-grade GenAI agents with reusable patterns and blueprints.

A comprehensive document search and storage platform for building AI applications using Python.

DeepAnalyze is an agentic LLM for autonomous data science, automating data analysis and report generation.

An AI-driven local automation assistant that uses natural language to make computers work by themselves.

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

On-device multimodal LLM for vision, speech, and live streaming on phones

A customizable, multi-modal AI chatbot that can be integrated with various chat platforms and leverages LLMs like ChatGPT, Bard, and GPT-3.

Preswald is a WASM packager for Python-based interactive data apps that can be run completely in-browser.

A powerful Python framework for building real-time voice AI agents powered by OpenAI and other AI tools.

A flexible and fast reinforcement learning library for building LLM-powered agents and reasoning systems.

A Spring-based framework for building AI-powered applications and services.

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

A Python project that enables natural, spoken conversations with AI using real-time voice chat.

RAG-based chat UI for document QA with customizable LLM support

DiffSynth-Studio is a Python library that allows developers to enjoy the magic of Diffusion models.

Python robotics algorithms and textbook for developers.

RAG & Agent app for LLMs with local knowledge base support

A course on building a tiny vLLM (virtual Large Language Model) and Qwen inference serving on Apple Silicon for systems engineers.

Curated list of Chinese open-source LLMs, including base models, fine-tuning, and applications

FinGPT is an open-source financial large language model that can be used for various fintech applications.

Tool to remove image backgrounds using AI

Official repo for a paper on scalable and versatile 3D generation using structured 3D latents.

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

An open-source, scalable, and high-performance RL framework for building AI-powered applications and tools.

An ongoing research project focused on training large language models at scale using transformers.

Open-source framework for building AI-powered apps in JavaScript, Go, and Python, used in production by Google.

Latent text-to-image diffusion model for generating images from text prompts

A Python library that uses OpenAI's Whisper to enable offline audio transcription and translation.

Triton is a development repository for a domain-specific programming language and compiler focused on machine learning and AI workloads.

A fast BPE tokenizer for use with OpenAI's language models in Python.

Kodezi Chronos is a state-of-the-art debugging-first language model for code analysis and bug fixing.

A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.

A lightweight, state-of-the-art text-to-speech (TTS) model for developers building AI-powered applications.

A curated list of awesome papers and code for optimizing LLM/VLM inference performance

Open-source end-to-end enterprise-grade intelligent agent platform for vibe coders.

AI observability and evaluation tooling for developers building with large language models and AI agents.

A Python library for generating structured outputs from language models like OpenAI's GPT-3.

An ultra-realistic text-to-speech model for generating natural-sounding dialogue and audio.

Nugget is a Python library that unlocks the full potential of your device with AI-powered tools and features.

AI-powered wearable device that transcribes speech and summarizes conversations for developers.

Kimi K2 is a large language model series developed by Moonshot AI team for AI-powered coding tools and applications.