2025 AI Open Source Project Fastest Star Growth Ranking

An open-source tool that quickly clones and rebuilds any website into a modern React application through AI conversation.

Microsoft's open-source, cutting-edge multi-speaker conversational text-to-speech AI model, supporting the generation of expressive dialogue audio of up to 90 minutes with up to 4 different speakers.

Transforms entire websites into LLM-ready Markdown or structured data, with scraping, crawling, and extraction through a single API.

GitHub's open-source specification-driven development toolkit that guides AI coding assistants to generate high-quality code through structured specifications and plans.

AI-powered browser automation framework that combines natural language and code to control browsers

An open-source Faircode workflow automation platform with native AI capabilities, combining visual building and custom code, supporting 400+ integrations.

A lightweight GPT training framework that allows you to train a small 26M parameter language model from scratch in just 2 hours.

Claude AI Skills Library - A reusable set of instructions for teaching Claude to perform specialized tasks

Meta's open-source multilingual speech recognition system supporting over 1,600 languages

PaddleOCR aims to create a rich, leading, and easy-to-use OCR toolkit to help developers train better, faster, and more accurate OCR models.

A powerful low-code AI application building platform designed for creating intelligent agents and RAG applications.

A feature-rich, self-hosted AI chat interface that supports Ollama and OpenAI API, providing a completely offline AI conversation experience.

Gemini CLI is Google's official open-source AI command-line tool that integrates Gemini AI capabilities directly into the terminal.

Build a ChatGPT Clone for $100 - A Single-File Full-Stack LLM Implementation

An open-source AI agent tool that automates browser workflows using LLM and computer vision technologies.

A free and open-source OpenAI alternative that supports local deployment and inference, allowing you to run large language models without a GPU.

vllm is a fast and easy-to-use library for fast inference of large language models.

LightRAG is a simple and fast Retrieval-Augmented Generation framework that supports multiple query modes and knowledge graph construction.

An open-source LLM application development platform that integrates agent workflows, RAG pipelines, model management, and more, allowing you to quickly go from prototype to production deployment.

An efficient OCR model based on visual compression, capable of converting document images into Markdown format, supporting multi-resolution and multi-language recognition.

A powerful and modular Stable Diffusion visual interface with node-based workflow design.

Milvus is a high-performance, cloud-native open-source vector database built for large-scale vector similarity search in AI and GenAI applications.

Claude Code Router, allows routing Claude Code requests to different AI models, supporting multi-model collaboration and cost optimization.

Enables AI programming assistants to control and inspect the MCP server in Chrome browser, providing automation, debugging, and performance analysis capabilities.

An open-source AI agent workflow builder, providing a lightweight visual interface for quickly building and deploying LLM applications that connect various tools.

An open-source Retrieval-Augmented Generation engine based on deep document understanding, providing accurate and reliable question answering capabilities for businesses of all sizes.

Ollama: Run, create, and share large language models locally.

llama.cpp is a LLaMA model inference engine written in pure C/C++, designed for high performance and low resource usage.

A no-code, low-code large language model fine-tuning and deployment framework that supports unified and efficient fine-tuning of 100+ LLMs/VLMs.

IndexTTS is an industrial-grade, controllable, and efficient zero-shot text-to-speech system built on XTTS and Tortoise, supporting Chinese Pinyin error correction and precise voice control.

An open-source project providing an intelligent memory layer for AI agents and assistants, enabling personalized AI interaction experiences.

An open-source framework providing AI agents with memory capabilities using 5 lines of code.

MediaCrawler is a powerful multi-platform social media crawler tool.

JD.com's open-source, end-to-end, production-grade general multi-agent framework, supporting out-of-the-box intelligent agent application development.

Google's official preview project of the Gemini 2.5 Computer Use model, supporting an AI agent that controls the browser to perform tasks through natural language instructions.

A multi-agent financial trading framework based on large language models, simulating the collaborative structure of real trading firms.

Serena is a powerful coding agent toolkit that transforms large language models (LLMs) into a fully functional agent, working directly on your codebase.

A real-time temporal knowledge graph construction framework for AI agents

A multi-agent LLM-based Chinese financial trading decision-making framework that utilizes a team of professional analysts to collaborate on stock analysis and investment decisions.

YOLOv5 is a state-of-the-art, real-time object detection model based on PyTorch, supporting object detection, image segmentation, and image classification tasks.

Open-source, high-performance web crawler and data extraction tool optimized for LLMs and AI agents.

The easiest way for AI agents to connect to and control browsers, enabling website automation.

Unified LLM API gateway, supporting OpenAI format calls for 100+ large language model providers

Cherry Studio is a desktop AI assistant client that supports multiple large language models and is compatible with Windows, Mac, and Linux systems.

Transformers provides thousands of pre-trained models to support tasks in over 100 languages across text, vision, audio, and more.

Playwright-based Model Context Protocol (MCP) server providing browser automation capabilities for LLMs

Unsloth: Efficient fine-tuning and reinforcement learning tool for large language models - 2x faster training, 70% less memory usage

An AI-based open-source quantitative investment platform that provides a complete machine learning pipeline for financial data modeling and investment strategy development.

A multi-agent collaborative automation framework that enables AI agents to work together like team members to execute complex tasks.

Open-source intelligent agent browser with local AI automation and privacy protection.