Latest Active Updates for AI Open Source Projects in 2025

An open-source, modern AI chat framework that supports multiple AI providers, knowledge base management, multimodal interaction, and more.

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

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

Open-source vector database supporting semantic search, hybrid queries, and AI model integration

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 open-source machine learning framework for everyone

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

An open-source enterprise-level AI knowledge base question answering system based on large language models and RAG technology, supporting workflow orchestration and MCP tool calls.

A lightweight multi-agent system development framework with support for memory, knowledge, and reasoning capabilities.

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

Flax is a neural network library designed for high-performance machine learning research, built on JAX.

An open-source OpenTelemetry Collector distribution with programmable pipelines and built-in Prometheus support

A powerful Node.js web scraping and browser automation library with JavaScript and TypeScript support, capable of extracting data for AI, LLM, RAG, etc.

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

An advanced diffusion model library for image, video, and audio generation.

AutoGPT is a powerful AI automation platform that makes it easy for anyone to create, deploy, and manage continuous AI agents to automate complex workflows.

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

A high-performance, open-source vector database built with Rust, providing fast and scalable vector similarity search for the next generation of AI applications.

🤗 PEFT is an advanced Parameter-Efficient Fine-Tuning library developed by Hugging Face, enabling low-cost fine-tuning of large models through techniques like LoRA and AdaLoRA.

PyTorch: Python tensor and dynamic neural network with strong GPU acceleration

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

Colossal-AI: Making large model training easy, efficient, and cost-effective.

A leading AI creative engine based on Stable Diffusion, providing powerful AI image generation and editing tools for professionals and artists.

Production-ready platform with 250+ tool integrations for AI agents and large language models, enabling seamless connectivity through function calling.

JAX is a Python library for high-performance numerical computation and machine learning. It combines the ease of use of NumPy with the power of automatic differentiation and can run on CPUs, GPUs, and TPUs.

GitHub MCP Server is a Model Context Protocol (MCP) server designed to seamlessly integrate with the GitHub API, providing developers and tools with advanced automation and interaction capabilities.

An LLM-based intelligent knowledge base platform that provides data processing, RAG retrieval, and AI workflow orchestration capabilities.

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

A free and open-source web-based video editor, an alternative to CapCut, supporting privacy protection and watermark-free editing.

A scalable generative AI framework built for researchers and developers, focusing on large language models, multi-modal AI, and speech AI (automatic speech recognition and text-to-speech)

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference, supporting deep learning applications such as computer vision, automatic speech recognition, generative AI, and natural language processing.

A TypeScript-based AI agent framework for quickly building AI applications and features.

Streamlit is a Python library that allows you to create beautiful, custom web applications with pure Python code for machine learning, data science, and more.

A feature-rich Model Context Protocol (MCP) gateway and registry that provides unified management of tools, resources, and prompts, supports REST API to MCP protocol conversion, and features security and observability.

The simplest way to deploy AI applications and model services - build model inference APIs, task queues, LLM applications, multi-model pipelines, etc.

PaddlePaddle, based on the open-source deep learning platform, integrates deep learning training and inference frameworks, model libraries, tool components, and service platforms. It features leading development convenience, ultra-large-scale training capabilities, multi-end and multi-platform deployment capabilities, and full-stack technology autonomy and controllability.

An acceleration inference and training library providing hardware optimization tools for Transformers, Diffusers, TIMM, and Sentence Transformers.

ElevenLabs official MCP server, supporting AI audio processing functions such as text-to-speech, voice cloning, and audio transcription.

MCP Database Toolbox is an open-source MCP server designed to simplify database tool development, providing features like connection pooling and authentication.

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

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

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

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

OpenCV is an open-source computer vision, machine learning, and image processing library that provides a rich set of algorithms and tools, widely used in areas such as image recognition, object detection, and video analysis.

AI Query Engine - An open-source platform to build and deploy machine learning models on large-scale federated data sources using SQL syntax.

Scikit-learn: Machine learning library in Python, providing simple and efficient tools for data mining and data analysis.

An open-source, large-scale vector database and search engine platform that supports real-time inference and AI application building.

An intelligent Retrieval-Augmented Generation (RAG) platform based on generative AI, helping users build a second brain for intelligent document Q&A and knowledge management.

XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible and portable. It implements machine learning algorithms under the Gradient Boosting framework.

ONNX Runtime: A cross-platform, high-performance machine learning inference and training accelerator.