Project directory

Projects

Open-source AI projects tracked by the leaderboard, ordered by GitHub stars.

Python 9,880 stars

xuebinqin/U-2-Net

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

Overview: U2-Net, a novel architecture for salient object detection, has been introduced in our accepted paper at Pattern Recognition 2020. This project aims to enhance the accuracy and efficiency of salient object detection. Key features: - U2-Net architecture for improved salient object detection - Code available for research and development Tech stack: Python Why it matters: U2-Net offers a significant advancement in salient object detection, enhancing the accuracy and efficiency of the process, making it a valuable contribution to the field of computer vision and image processing. Repository: xuebinqin/U-2-Net Primary language: Python GitHub stars: 9879 GitHub description: The code for our paper "U<sup>2</sup>-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

Python 9,838 stars

aliasrobotics/cai

Cybersecurity AI (CAI), the framework for AI Security

### Overview: Cybersecurity AI (CAI) is an open-source framework established in 2025 by Alias Robotics. It revolutionized the field of AI security by providing a lightweight, research-focused solution for both offensive and defensive security automation. ### Key Features: - **Lightweight and Open-Source**: CAI is designed to be easily integrated into existing security systems without requiring extensive changes. - **Research-Driven**: The framework is built on the foundation of 18 published papers, including 30+ CVEs and #1 rankings in international security competitions. - **Versatile Capabilities**: It supports both offensive and defensive security automation, making it a versatile tool for security professionals. - **High Performance**: CAI is 3x faster than traditional security solutions and costs 156x less, making it highly cost-effective. - **Extensive Dataset**: The framework includes a trajectory corpus of 18.07 TB, providing a rich data set for security researchers. ### Tech Stack: Python ### Why it Matters: CAI has been instrumental in establishing Cybersecurity AI as a research domain, providing a solid foundation for further advancements in AI security. Its lightweight nature and open-source approach have made it a valuable tool for researchers and security professionals alike.

C++ 9,837 stars

Tiiny-AI/PowerInfer

High-speed Large Language Model Serving for Local Deployment

Overview: PowerInfer is a CPU/GPU LLM inference engine that leverages activation locality for efficient inference on consumer-grade GPUs, enabling high-speed processing of large language models. Key features: - TurboSparse-Mixtral-47B: Achieves 11.68 tokens per second, up to 22 times faster than other state-of-the-art frameworks. - SmallThinker models: Efficiently optimized for on-device inference. - Support for AMD devices with ROCm. Tech stack: C++ Why it matters: PowerInfer provides a fast and efficient solution for large language model inference, making it suitable for real-time applications and remote work environments.

Python 9,831 stars

roboflow/rf-detr

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

Overview: RF-DETR is a real-time object detection, instance segmentation, and keypoint detection model architecture designed by Roboflow for fine-tuning. It is built on a DINOv2 vision transformer backbone and is optimized for real-time performance. Key features: - Real-time object detection - Real-time instance segmentation - Real-time keypoint detection (preview) Tech stack: Python Why it matters: RF-DETR delivers state-of-the-art accuracy and latency trade-offs on Microsoft COCO and RF100-VL. It is designed for real-time applications and supports object detection, instance segmentation, and keypoint detection in a single, consistent API.

Python 9,817 stars

jadore801120/attention-is-all-you-need-pytorch

A PyTorch implementation of the Transformer model in "Attention is All You Need".

Overview: This is a PyTorch implementation of the Transformer model from the paper "Attention is All You Need" by Vaswani et al., focusing on the WMT 2014 English-to-German translation task. It features a self-attention mechanism and achieves state-of-the-art performance. Key features: - Self-attention mechanism - State-of-the-art performance on WMT 2014 English-to-German translation task - Support for training and translation with a trained model Tech stack: PyTorch Why it matters: This project demonstrates the effectiveness of the Transformer model in natural language processing tasks, showcasing the importance of self-attention in sequence-to-sequence tasks. Repository: jadore801120/attention-is-all-you-need-pytorch Primary language: Python GitHub stars: 9817

Python 9,787 stars

Lightricks/LTX-2

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Overview: LTX-2 is an official Python inference and LoRA trainer package for the LTX-2 audio-video generative model, designed for developers and researchers. Key features: - Official Python inference and LoRA trainer package - Supports multiple performance modes - Provides synchronized audio and video - Offers production-ready outputs - Includes API access - Open access to the model Tech stack: Python Why it matters: LTX-2 simplifies the process of using and training the LTX-2 model, making it accessible to developers and researchers alike.

TypeScript 9,757 stars

mobile-next/mobile-mcp

Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)

### Overview: The Mobile Next - MCP server is a scalable tool designed for mobile automation and scraping across iOS and Android devices, emulators, simulators, and real devices. It provides a platform-agnostic interface, enabling seamless interaction with native iOS/Android applications and devices through structured accessibility snapshots or coordinate-based taps. ### Key Features: - **Accessibility-first**: Drives apps from the native accessibility tree, falling back to screenshots and coordinates only when necessary. - **One API, every target**: The same tools work across iOS and Android, including simulators, emulators, and real devices. - **No platform expertise**: Simplifies mobile automation by eliminating the need for distinct iOS or Android knowledge. ### Tech Stack: TypeScript ### Why It Matters: This server facilitates efficient and cost-effective mobile automation, making it ideal for developers looking to streamline their testing and data entry processes. Its platform-agnostic nature ensures compatibility across various devices and tools, enhancing flexibility and reducing setup requirements. Repository: mobile-next/mobile-mcp Primary Language: TypeScript GitHub Stars: 9703 GitHub Description: Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)

Java 9,731 stars

apache/seatunnel

SeaTunnel is a multimodal, high-performance, distributed, massive data integration tool.

Overview: SeaTunnel is a multimodal, high-performance, distributed data integration tool designed for efficient and stable data synchronization across various sources. Key features: - Seamlessly integrates with hundreds of data sources. - Supports diverse data types including video, images, binary files, structured and unstructured text data. - Simplifies data integration management with batch-stream integration. - Works with SeaTunnel Zeta Engine, Flink, and Spark. - Efficiently synchronizes multi-tables and databases. - Provides high-throughput data synchronization with low latency. - Offers detailed monitoring during synchronization. Tech stack: Java Why it matters: SeaTunnel addresses common data integration challenges, ensuring efficient and stable data synchronization across diverse sources. Repository: apache/seatunnel GitHub stars: 9733

Jupyter Notebook 9,719 stars

roboflow/notebooks

A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL.

Overview: This repository contains tutorials on various computer vision models and techniques, including foundational architectures like ResNet and cutting-edge models such as RF-DETR, YOLO11, SAM 3, and Qwen3-VL. Key features: - State-of-the-art computer vision models - Tutorials on object detection, segmentation, pose estimation, and more - Complementary materials for further learning Tech stack: Jupyter Notebook Why it matters: Explore the latest advancements in computer vision through these comprehensive tutorials, making it easier to understand and apply cutting-edge models in various tasks. Repository: roboflow/notebooks GitHub stars: 9717

Python 9,615 stars

xorbitsai/inference

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

### Overview: Xorbits Inference is a unified, production-ready inference API that allows you to run open-source, speech, and multimodal models on cloud, on-prem, or your laptop. ### Key features: - Deploy any model, including open-source, speech, and multimodal models. - Use a single command to serve models. - Supports cloud, on-prem, and local deployments. - Integrates with Xagent for dynamic planning and multi-step reasoning. - Automatically batches multiple concurrent requests for improved throughput. ### Tech stack: Python ### Why it matters: Xorbits Inference simplifies the deployment and serving of AI models, making it accessible to researchers, developers, and data scientists.

TypeScript 9,569 stars

anthropics/claude-code-action

### Overview: Claude Code Action is a versatile tool designed to enhance collaboration and productivity on GitHub projects. It integrates Claude AI for intelligent code assistance, enabling users to ask questions and implement code changes seamlessly. ### Key features: - **Intelligent Mode Detection**: Automatically selects the appropriate execution mode based on workflow context. - **Interactive Code Assistant**: Answers questions about code, architecture, and programming. - **Code Review**: Analyzes PR changes and suggests improvements. - **Code Implementation**: Can implement simple fixes, refactoring, and new features. - **PR/Issue Integration**: Works with GitHub comments and PR reviews. - **Flexible Tool Access**: Access to GitHub APIs and file operations. - **Progress Tracking**: Visual progress indicators with checkboxes. - **Structured Outputs**: Validates JSON results for GitHub Action outputs. - **Runs on Your Infrastructure**: Executes on your own GitHub runner. - **Simplified Configuration**: Unified `prompt` and `claude_args` inputs. ### Tech stack: TypeScript ### Why it matters: This action streamlines the workflow by automating essential tasks such as code review and implementation, making it easier for developers to collaborate and improve their projects.

Python 9,562 stars

PeterL1n/RobustVideoMatting

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

**Overview:** Robust Video Matting (RVM) is a powerful tool designed for real-time human video matting, achieving 4K 76FPS and HD 104FPS performance on an Nvidia GTX 1080 Ti GPU. The project is based on the paper "Robust High-Resolution Video Matting with Temporal Guidance," which has been accepted by WACV 2022. **Key features:** - Real-time video matting - Robust performance across various resolutions - Uses a recurrent neural network for temporal memory - Compatible with PyTorch, TensorFlow, TensorFlow.js, ONNX, and CoreML **Tech stack:** Python **Why it matters:** RVM offers a significant improvement in accuracy and efficiency compared to existing models, making it ideal for applications requiring high-resolution and real-time video processing, such as video editing, content-aware style transfer, and more. **Repository:** PeterL1n/RobustVideoMatting **GitHub stars:** 9561 **GitHub description:** Official repository for the paper "Robust High-Resolution Video Matting with Temporal Guidance." RVM is specifically designed for robust human video matting. Unlike existing neural models that process frames as independent images, RVM uses a recurrent neural network to process videos with temporal memory. RVM can perform matting in real-time on any videos without additional inputs. It achieves **4K 76FPS** and **HD 104FPS** on an Nvidia GTX 1080 Ti GPU

Java 9,553 stars

spring-projects/spring-ai

An Application Framework for AI Engineering

### Overview: Spring AI is an application framework designed to integrate AI models with enterprise data and APIs, leveraging Spring ecosystem principles for a more structured and modular approach. ### Key Features: - **Model Support**: Supports major AI model providers including Anthropic, OpenAI, Amazon Bedrock, Google, Ollama, Mistral AI, DeepSeek, and more. - **Model Types**: Chat, Embedding, Text to Image, Audio Transcription, Text to Speech, Moderation. - **API Portability**: Provides a portable API across different AI providers, offering both synchronous and streaming options. - **Structured Outputs**: Supports structured output mapping to POJOs. - **Vector Store Integration**: Integrates with vector stores like Amazon Bedrock Knowledge Base, Amazon S3, Apache Cassandra, Azure Vector Search, Chroma, Couchbase, Elasticsearch, GemFire, MariaDB, Milvus, MongoDB Atlas, Neo4j, OpenSearch, Oracle, PostgreSQL/PGVector, Pinecone, Qdrant, Redis, Typesense, and Weaviate. ### Tech Stack: Java ### Why It Matters: Spring AI simplifies the integration of AI models with enterprise data and APIs, making it easier to build robust and scalable applications. Its modular design and strong typing principles align well with Spring's ecosystem, ensuring a cohesive and maintainable solution.

Python 9,552 stars

sloria/TextBlob

Simple, Pythonic, text processing--Sentiment analysis, part-of-speech tagging, noun phrase extraction, translation, and more.

Overview: TextBlob is a Python library designed for simple text processing tasks, including sentiment analysis, part-of-speech tagging, noun phrase extraction, translation, and more. Key features: - Noun phrase extraction - Part-of-speech tagging - Sentiment analysis - Classification (Naive Bayes, Decision Tree) - Tokenization - Word and phrase frequencies - Parsing - n-grams - Word inflection (pluralization and singularization) and lemmatization - Spelling correction - Add new models or languages through extensions Tech stack: Python Why it matters: TextBlob simplifies common NLP tasks, making it accessible for developers looking to integrate text processing into their projects.

TypeScript 9,543 stars

olistic/warriorjs

🏰 An exciting game of programming and Artificial Intelligence

Overview: WarriorJS is an engaging game that teaches JavaScript and TypeScript through programming challenges, focusing on strategic thinking and logic. Key features: - Writing code to guide a warrior through various levels with puzzles. - Learning JavaScript and TypeScript by writing game logic. - No clicking or dragging; only logic and sharp thinking required. Tech stack: TypeScript Why it matters: WarriorJS is an excellent way to learn JavaScript and TypeScript while developing essential programming skills, including problem-solving and strategic thinking. Repository: olistic/warriorjs Primary language: TypeScript GitHub stars: 9,543 GitHub description: 🏰 An exciting game of programming and Artificial Intelligence README excerpt: <div align="center"> <a href="https://warrior.js.org"> <img alt="WarriorJS Banner" title="WarriorJS" src="logo/warriorjs-banner-dark.png?raw=true"> </a> </div> <br /> <div align="center"> <strong>Learn JavaScript and TypeScript by writing code that fights</strong> </div> <br /> <div align="center"> <a href="https://github.com/olistic/warriorjs/actions/workflows/ci.yml"> <img alt="CI" src="https://img.shields.io/github/actions/workflow/status/olistic/warriorjs/ci.yml?branch=master&style=flat-square"> </a> <a href="https://codecov.io/gh/olistic/warriorjs"> <img alt="Codec

C 9,531 stars

QwenAudio/SenseVoice

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

### Overview SenseVoice is an open-source speech foundation model designed for high-accuracy multilingual speech recognition, spoken language identification, speech emotion recognition, and audio event detection. It supports Mandarin, Cantonese, English, Japanese, and Korean. The model achieves state-of-the-art performance on various benchmarks and is widely used in real-world applications. ### Key Features - **Multilingual Support:** Supports ASR, LID, SER, and AED for Mandarin, Cantonese, English, Japanese, and Korean. - **Emotion Recognition:** Achieves and surpasses current best emotion recognition models on test data. - **Sound Event Detection:** Detects various common human-computer interaction events such as background music, applause, laughter, crying, coughing, and sneezing. - **Efficient Inference:** Uses a non-autoregressive end-to-end framework for low-latency inference. - **Convenient Finetuning:** Provides scripts and strategies for easy finetuning. - **Service Deployment:** Supports multi-concurrent requests with client-side languages including Python, C++, HTML, Java, and C#. ### Tech Stack The primary language used is C. ### Why It Matters SenseVoice is crucial for applications requiring high-accuracy speech recognition, emotion detection, and audio event detection across multiple languages, making it indispensable in various industries and research domains.

Rust 9,470 stars

databendlabs/databend

Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from scratch. Unified architecture on your S3.

Overview: Databend is an open-source enterprise data warehouse built in Rust, designed for large-scale analytics, vector search, and full-text search. It supports flexible agent orchestration and secure Python UDF sandboxes, making it ideal for enterprise AI workloads. Key features: - Unified architecture on S3 - Built-in analytics, vector search, and full-text search capabilities - Agent-ready with sandbox UDFs and SQL orchestration - Secure Python UDFs for agent logic - Reliable transactions and safe experimentation on production data Tech stack: Rust Why it matters: Databend offers a single engine for large-scale analytics, vector search, and full-text search, making it a comprehensive solution for enterprise AI workloads. Its agent-ready architecture supports flexible agent orchestration and secure Python UDFs, ensuring safe and reliable operations. Repository: databendlabs/databend GitHub stars: 9468

Rust 9,460 stars

ccfddl/ccf-deadlines

Agenticly track ccf-ranked & worldwide conference deadlines (Website, Python Cli, Wechat Applet)

Overview: CCF-Deadlines is a platform designed to help researchers track the deadlines and other important information for CCF-ranked and worldwide conferences. Key features: - Track worldwide conference deadlines - Collaborate with researchers globally - Access a website portal, WeChat applet, and tabular portal for easy tracking - Provide a Python CLI tool for command-line integration - Offer a Raycast extension for seamless integration into various platforms - Support iCal subscription and Chrome extension for calendar integration - Implement a Model Context Protocol (MCP) server for AI clients to search conferences and retrieve historical acceptance rates Tech stack: Rust Why it matters: CCF-Deadlines simplifies the process of tracking conference deadlines and other important information for researchers, making it easier for them to stay informed and prepare for upcoming events. The platform's collaboration features and various tracking methods make it an essential tool for researchers and conference organizers alike. Repository: ccfddl/ccf-deadlines Primary language: Rust GitHub stars: 9457 GitHub description: Agenticly track ccf-ranked & worldwide conference deadlines (Website, Python Cli, Wechat Applet) README excerpt: A platform designed to help researchers track the deadlines and other important information for CCF-ranked and worldwide conferences.

Rust 9,426 stars

xberg-io/xberg

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

### Overview: Xberg is a powerful tool for extracting text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, as well as providing code intelligence for 371 languages. It is built with Rust and leverages the Alef library for efficient and scalable processing. ### Key features: - **Text Extraction**: Extract text from various file formats. - **Metadata Extraction**: Retrieve metadata from documents. - **Image Extraction**: Extract images from PDFs and other image formats. - **Structured Data Extraction**: Extract structured data from spreadsheets and databases. - **Code Intelligence**: Provides code intelligence for 371 languages, including Python, Java, C#, and more. ### Tech stack: Rust ### Why it matters: Xberg is a highly efficient and versatile tool that simplifies the process of extracting and analyzing data from various file formats and languages. Its Rust implementation ensures fast performance and scalability, making it an essential tool for developers working across multiple languages and file types.

Python 9,419 stars

yzhao062/anomaly-detection-resources

Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!

Overview: This repository is a curated collection of books, academic papers, online courses, videos, datasets, and toolboxes related to anomaly detection. It serves as a valuable resource for developers and researchers interested in the field of anomaly detection, including both machine learning and deep learning approaches. Key features: - Books and academic papers - Online courses and videos - Outlier datasets - Open-source and commercial libraries/toolkits Tech stack: Python Why it matters: This repository provides a comprehensive overview of the latest techniques and resources in anomaly detection, making it an essential tool for anyone looking to enhance their knowledge and skills in this field.