Best Open Source AI Framework Projects

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

An Open Source Machine Learning Framework for Everyone

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Production-ready platform for agentic workflow development.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

💫 Toolkit to help you get started with Spec-Driven Development

real time face swap and one-click video deepfake with only a single image

Open Source Computer Vision Library

A collection of MCP servers.

List of Computer Science courses with video lectures.

The fastest path to AI-powered full stack observability, even for lean teams.

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Tesseract Open Source OCR Engine (main repository)

The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

scikit-learn: machine learning in Python

Deep Learning for humans

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Ultralytics YOLO 🚀

Deepfakes Software For All

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

LlamaIndex is the leading document agent and OCR platform

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

The Julia Programming Language

12 Weeks, 24 Lessons, AI for All!

Spec-driven development (SDD) for AI coding assistants.

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.

A community-supported supercharged document management system: scan, index and archive all your documents

AI-Powered Photos App for the Decentralized Web 🌈💎✨

We write your reusable computer vision tools. 💜

Pure Javascript OCR for more than 100 Languages 📖🎉🖥

Google Research

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Cross-platform, customizable ML solutions for live and streaming media.

💫 Industrial-strength Natural Language Processing (NLP) in Python

Visualizer for neural network, deep learning and machine learning models

Playwright MCP server

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

GitHub's official MCP Server

:memo: An awesome Data Science repository to learn and apply for real world problems.

A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visualization.

An AI prompt optimizer for writing better prompts and getting better AI results.

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

The fastai deep learning library

Integrate cutting-edge LLM technology quickly and easily into your apps

deep learning for image processing including classification and object-detection etc.

The Modular Platform (includes MAX & Mojo)

南瓜书：《机器学习》（西瓜书）公式详解

Your ultimate Go microservices framework for the cloud-native era.

⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 or handson-mlp instead.

A game theoretic approach to explain the output of any machine learning model.

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

Bitmap & tilemap generation from a single example with the help of ideas from quantum mechanics

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

Machine Learning Systems

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

Graph Neural Network Library for PyTorch

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Learn OpenCV : C++ and Python Examples

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

CVPR 2026 论文和开源项目合集

Best Practices on Recommendation Systems

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

Open standard for machine learning interoperability

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

"RAG-Anything: All-in-One RAG Framework"

A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

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

Official, Anthropic-managed directory of high quality Claude Code Plugins.

An open source cybersecurity protocol for syncing decentralized graph data.

:book: A curated list of resources dedicated to Natural Language Processing (NLP)

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

Streaming music player that finds free music for you

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms

📻Terminal/ssh/sftp/ftp/telnet/serialport/RDP/VNC/Spice client(linux, mac, win)

OpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.

MCP for xiaohongshu.com

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection

Show usage stats for OpenAI Codex and Claude Code, without having to login.

🍌 World's largest Nano Banana Pro prompt library — 10,000+ curated prompts with preview images, 16 languages. Google Gemini AI image generation. Free & open source.

This repository contains demos I made with the Transformers library by HuggingFace.

Force Remove Copilot, Recall and More in Windows 11

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

OCR model that handles complex tables, forms, handwriting with full layout.

Open source MCP Servers for AWS

An AI-powered search engine with a generative UI

Cybersecurity AI (CAI), the framework for AI Security

High accuracy RAG for answering questions from scientific documents with citations

A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.

BertViz: Visualize Attention in Transformer Models

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

Open-source, self-hosted CMS platform on AWS serverless (Lambda, DynamoDB, S3). TypeScript framework with multi-tenancy, lifecycle hooks, GraphQL API, and AI-assisted development via MCP server. Built for developers at large organizations.

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

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

🚀 通用 AI IDE 账号管理工具：支持 Antigravity / Codex / GitHub Copilot / Windsurf / Kiro / Cursor / Gemini-cli / CodeBuddy，多账号切换、配额监控、自动唤醒与多开实例管理。 🚀 Universal AI IDE account manager for Antigravity / Codex / GitHub Copilot / Windsurf / Kiro / Cursor / Gemini-cli / CodeBuddy, with multi-account switching, quota monitoring, wake-up automation, and multi-insta

Monitor browser logs directly from Cursor and other MCP compatible IDEs.

PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.

MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients

A community driven registry service for Model Context Protocol (MCP) servers.

A collection of MCP clients.

Open-source offline translation library written in Python

A concise but complete full-attention transformer with a set of promising experimental features from various papers

🚀 World's largest GPT Image 2 prompt library, updated daily — 2000+ curated prompts with preview images, 16 languages. OpenAI's next-gen image model with pixel-perfect text rendering, cross-image consistency, and commercial-grade illustration. Free & open source.

A machine learning software for extracting information from scholarly documents

Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

ML-powered manga translator, written in Rust.

中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

An open source extension that connects AI agents to computational notebooks in JupyterLab.

The Hugging Face course on Transformers

Scenic: A Jax Library for Computer Vision Research and Beyond

Synthetic data generation for tabular data

A Unified Library for Parameter-Efficient and Modular Transfer Learning

ALLWEONE® Open source AI presentation generator Gamma Alternative. Create professional slides with customizable themes and AI-generated content in minutes.

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.

Local Twitter/X bookmark organizer with AI categorization and mindmap visualization

The Self-Coding System for Your App — Alan AI SDK for Web

Youtube client with older Android version support, background player, Google Gemini ✨ and many more features.

[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

MLX native implementations of state-of-the-art generative image models

A collection of 🤗 Transformers.js demos and example applications

Transformers 库快速入门教程

Efficient Retrieval Augmentation and Generation Framework

국가법령정보MCP v4.0 | 법제처 41개 API → 17개 MCP 도구. 법령·판례·조례 검색 + LLM 환각 방지 인용검증 + 조문 영향 그래프(impact_map) + 시점 비교 자동 diff(time_travel) + 시민 5단계 실행 가이드(action_plan) | 41 Korean legal APIs → 17 MCP tools

ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week.

Open-source GEO content production system with AI tasks, review workflow, and publishing.

🚀 Rust 全量重构的 Claude Code - 性能提升 2.5x，体积减少 97% | High-performance Rust implementation of Claude Code with 2.5x faster startup and 97% smaller binary

This is NOT a third-party Claude Code client. ClawGod is a runtime patch applied on top of the official Claude Code. It works with any version — as Claude Code updates, the patch continues to take effect

🌙 ZetaLib - The only AI Library you need

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.