Project directory

Projects

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

Python 382 stars

PathologyFoundation/plip

Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI (Nature Medicine). PLIP is a large-scale pre-trained model that can be used to extract visual and language features from pathology images and text description. The model is a fine-tuned version of the original CLIP model.

Overview: Pathology Language and Image Pre-Training (PLIP) is a large-scale pre-trained model designed for pathology AI, enabling the extraction of visual and language features from pathology images and text descriptions. Key features: - Fine-tuned version of the original CLIP model - Supports both vision and language tasks - Utilizes CLIP for image and text encoding Tech stack: Python Why it matters: PLIP is a crucial foundational model for pathology AI, providing a robust framework for image and text analysis, which is essential for diagnosing and understanding diseases from medical images and patient reports. Repository: PathologyFoundation/plip Primary language: Python GitHub stars: 382 GitHub description: Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI. It is a large-scale pre-trained model that can extract visual and language features from pathology images and text descriptions. The model is a fine-tuned version of the original CLIP model.

JavaScript 382 stars

aichaos/rivescript-js

A RiveScript interpreter for JavaScript. RiveScript is a scripting language for chatterbots.

Overview: This is a JavaScript library that interprets RiveScript, a scripting language for building chatbots, allowing developers to create intelligent bots using a web browser or Node.js environment. Key features: - Supports both web browser and Node.js environments - Provides a way to load RiveScript documents (.rive files) and individual files - Allows for asynchronous file loading - Stores user variables in Redis for better performance - Provides a command-line interactive shell for testing bots Tech stack: JavaScript Why it matters: This library simplifies the development of chatbots by providing a straightforward way to write and run RiveScript scripts, making it easier to create engaging and intelligent chatbot interactions. Repository: aichaos/rivescript-js GitHub stars: 382

JavaScript 382 stars

devswha/patina

AI-writing humanizer for KO/EN/ZH/JA

### Overview: Patina is a deterministic, pattern-based humanizer designed for Korean, English, Chinese, and Japanese. It strips the AI packaging while preserving the meaning, making it ideal for allowed AI-assisted drafting. ### Key Features: - **Auditable, Not a Black Box:** 189 named patterns drive every edit, and `--diff` shows exactly what changed and why. - **Meaning Verified on the Web:** Web gates each rewrite with MPS/fidelity floors, rejecting drift; CLI `--verify` and `/patina --strict` add checks. - **Three Independent Axes:** Document Type owns genre, Persona owns voice, Register owns delivery. Omit any axis to preserve the source. - **Every Surface:** Agent skill (Claude Code · Codex · Cursor · OpenCode), Node CLI, and a browser playground. - **Honest About Limits:** Scores are editing signals, not authorship proof; our own pre-registered study publishes where rewriting fails alongside where it works. ### Why It Matters: Patina is a powerful tool for AI-assisted drafting that respects the integrity of the original text, ensuring that the meaning remains intact while still being useful for AI-assisted writing.

Unknown 382 stars

frutik/Awesome-RAG

### Overview: This project aims to provide an overview and detailed explanation of Retrieval-Augmented Generation (RAG), a technique that integrates LLMs with vector databases to enhance the generation of text-based responses. RAG is particularly useful in applications where context is critical and the quality of the output is paramount. ### Key Features: - **Disadvantages of RAG**: Discusses common issues and limitations of RAG systems. - **Patterns**: Explains various patterns and strategies for building and optimizing RAG systems. - **Dialogue Routing**: Describes the principles and practices of routing in RAG-driven applications. - **LLM Models**: Covers the process of finetuning and pretraining LLMs. - **Retrieval**: Discusses vector retrieval, including chunking and embeddings, and how they are used in RAG systems. - **Graph RAG**: Explores the integration of graph structures with RAG systems. - **Not Vector Retrieval**: Provides an alternative approach to RAG without relying on vector databases. - **Prompts**: Discusses various prompt strategies for RAG systems, including multi-modal, multi-index, and chain-of-verification. - **Generation**: Covers techniques for generating text that is both hallucinatory and well-grounded. - **Evaluation**: Provides methods for evaluating the performance and cost of RAG systems. - **Privacy and Security**: Addresses concerns such as context overload and potential injections. - **Applications of RAG**: Explores use cases in chatbots and other applications. - **Tools**: Lists various tools and libraries used

Python 381 stars

AnubhavChaturvedi-GitHub/jarvis-ai-assistant

Voice-controlled AI desktop assistant in Python. Speech recognition, text to speech, real-time web search, image generation, computer vision and WhatsApp automation, inspired by Iron Man's JARVIS.

Overview: J.A.R.V.I.S is a Python-based voice-controlled AI assistant inspired by Iron Man's JARVIS. It offers a wide range of functionalities including speech recognition, text-to-speech, real-time web search, image generation, computer vision, and WhatsApp automation. Key features: - Custom speech-to-text engine - Natural spoken replies - Language model reasoning and conversation memory - Live web search for answers - Image generation from spoken prompts - Camera and image understanding - Desktop and app control - WhatsApp messaging - Weather updates by location - Alarms and scheduling Tech stack: Python, SpeechRecognition, Selenium, PyWhatKit, OpenCV, Requests, Tkinter. Why it matters: J.A.R.V.I.S is designed to be offline-friendly and user-friendly, making it accessible to a wide audience. It's built with modular components, allowing developers to easily integrate only the features they need, making it highly versatile and adaptable. GitHub stars: 377, indicating a growing interest in this project.

Python 381 stars

EulerSearch/embedding_studio

Embedding Studio is a framework which allows you transform your Vector Database into a feature-rich Search Engine.

### Overview: Embedding Studio is an open-source framework designed to transform embedding models and vector databases into comprehensive, self-improving search engines. It includes built-in clickstream collection, continuous model refinement, and intelligent vector optimization, creating a feedback loop that enhances search quality over time based on real user interactions. ### Key Features: - 🔄 **Full-Cycle Search Engine** - Transform your vector database into a complete search solution. - 🖱️ **User Feedback Collection** - Automatically gather clickstream and session data. - 🚀 **Continuous Improvement** - Enhance search quality on-the-fly without long waiting periods. - 📊 **Performance Monitoring** - Track search quality metrics through comprehensive dashboards. - 🎯 **Iterative Fine-Tuning** - Improve your embedding model through user interaction data. - 🔍 **Blue-Green Deployment** - Zero-downtime deployment of improved embedding models. - 💾 **Multi-Source Integration** - Connect to various data sources (S3, GCP, PostgreSQL, etc.). - 🧠 **Vector Optimization** - Apply post-training adjustments for incremental improvements. ### Tech Stack: Python ### Why It Matters: Embedding Studio is an innovative framework that helps businesses and developers transform their vector databases into powerful search engines. By continuously refining and improving based on user feedback, it enhances search quality and personalization, making it an essential tool for businesses looking to improve their search capabilities. ### Repository: GitHub: EulerSearch/embedding_studio Stars: 381 Description: Embedding Studio is a

TypeScript 381 stars

Nashex/gpt4-playground

Clone of OpenAI's ChatGPT and Playground environments to enable experimenting with API keys.

Overview: This project is a clone of OpenAI's ChatGPT and Playground environments, designed to enable developers to experiment with API keys without the limitations of the current OpenAI Playground. Key features: - Mock ChatGPT Environment - Playground Environment Tech stack: TypeScript Why it matters: This project aims to fix the limitations of the current OpenAI Playground, allowing users to test out their API keys without compromising on either the experience or the performance. Repository: Nashex/gpt4-playground Primary language: TypeScript GitHub stars: 381 GitHub description: Clone of OpenAI's ChatGPT and Playground environments to enable experimenting with API keys.

Python 381 stars

Xiuyu-Li/q-diffusion

[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.

Overview: Q-Diffusion is a novel approach to quantizing diffusion models, enabling efficient inference while maintaining comparable performance. It achieves this by addressing the changing output distributions and bimodal activation distribution challenges of diffusion models. Key features: - Quantizes full-precision unconditional diffusion models into 4-bit while maintaining comparable performance. - Can be plugged into text-guided image generation to achieve high generation quality in 4-bit weights. - Provides official implementation with calibrated quantized checkpoints. Tech stack: Python Why it matters: Q-Diffusion offers a practical solution for quantizing diffusion models, making them more efficient and accessible for real-time applications without compromising quality.

Unknown 381 stars

gutfeeling/beginner_nlp

A curated list of beginner resources in Natural Language Processing

Overview: This repository is a curated list of beginner resources in Natural Language Processing (NLP), aimed at developers and learners. It includes books, MOOCs, YouTube videos, online courses, packages, academic papers, and more. Key features: - Books: A collection of classic and application-oriented textbooks on NLP. - MOOCs: Introduction to NLP, focusing on Python and practical applications. - YouTube Videos: Video series by Jurafsky and Martin, and an application-oriented video series using Python and NLTK. - Online University Courses: Machine Translation course at the University of Pennsylvania. - Packages to Play With: NLTK, a popular NLP library in Python with extensive documentation. Tech stack: Python, NLTK, and other relevant tools. Why it matters: This list serves as a comprehensive guide for beginners interested in NLP, providing a structured approach to learning and practicing NLP skills through various resources and tools. Repository: gutfeeling/beginner_nlp GitHub stars: 382 GitHub description: A curated list of beginner resources in Natural Language Processing

Java 381 stars

sashirestela/simple-openai

A Java library to use the OpenAI Api in the simplest possible way.

### Overview: Simple-OpenAI is a Java library designed to simplify the use of the OpenAI API by providing a consistent and straightforward interface. ### Key features: - **Chat Completion**: Supports text generation, streaming, function calling, vision, structured outputs, and audio. - **Real-time Features**: Enables real-time conversations and updates. - **Audio Example**: Demonstrates how to use the library for audio processing. - **Image Example**: Shows how to integrate the library with image recognition. - **Chat Completion Example**: Illustrates how to use the library for chat completions. - **Chat Completion with Streaming Example**: Demonstrates streaming capabilities. - **Chat Completion with Functions Example**: Shows how to use functions within chat completions. - **Chat Completion with Vision Example**: Integrates the library with vision-based features. - **Chat Completion with Audio Example**: Demonstrates audio processing. - **Chat Completion with Structured Outputs**: Supports structured output formats. - **Chat Completion Conversation Example**: A conversation example showcasing multiple interactions. - **Assistant v2 Conversation Example**: An example using the Assistant v2 feature. - **Response Conversation Example**: A conversation example using responses. - **Realtime Conversation Example**: A real-time conversation example. ### Tech stack: Simple-OpenAI utilizes the CleverClient library for HTTP communication, Jackson for JSON parsing, and Lombok to minimize boilerplate code. ### Why it matters: Simple-OpenAI simplifies the integration of OpenAI services into Java applications, making it easier for developers to leverage the full capabilities of the OpenAI API without the complexity of

Java 381 stars

spitfireuptown/datalinkx

🔥🔥DatalinkX异构数据源之间的数据同步系统，支持海量数据的增量或全量同步，同时支持HTTP、Oracle、MySQL、ES等数据源之间的数据流转，支持中间transform算子如SQL算子、大模型算子，底层依赖Flink、Seatunnel引擎，提供流转任务管理、任务级联配置、任务日志采集等功能🔥🔥

### Overview: DatalinkX是一个异构数据源之间的数据同步系统，支持海量数据的增量或全量同步，同时支持多种数据源如Oracle、MySQL、ES等之间的数据流转。它采用Flink和Seatunnel作为底层计算引擎，提供任务管理、任务级联配置和日志采集等功能。DatalinkX旨在提高企业内部数据协作效率，适用于大规模数据同步场景。 ### Key features: - 支持多种异构数据源之间的数据同步 - 支持全量和增量数据同步 - 支持HTTP、Oracle、MySQL、ES等数据源之间的数据流转 - 提供任务管理、任务级联配置、日志采集等功能 - 采用Flink和Seatunnel作为底层计算引擎 - 支持插件化加载数据源，方便自定义数据源的开发 ### Tech stack: DatalinkX的核心技术栈包括Spring Boot、Flink、Seatunnel等。 ### Why it matters: DatalinkX简化了企业内部数据协作的复杂性，通过集中管理同步任务和提高工作效率，帮助企业提升数据协作能力。其强大的数据同步能力和灵活的配置化功能使其成为大规模数据同步场景的理想选择。

Python 381 stars

stefanoamorelli/sec-edgar-mcp

A SEC EDGAR MCP (Model Context Protocol) Server

Overview: This project is a Model Context Protocol (MCP) server designed to connect AI assistants to SEC EDGAR filings, financial statements, and insider trading data, providing precise numeric precision. Key features: - Secure access to SEC EDGAR filings - Retrieval of 10-K, 10-Q, and 8-K filings - Extraction of company facts and company info - Retrieval of balance sheet, income statement, and cash flow data (XBRL-parsed) - Support for Form 3/4/5 transactions Tech stack: Python 3.11+ Why it matters: This MCP server provides a reliable and precise way to access financial information, enhancing the capabilities of AI assistants in the financial domain. Repository: stefanoamorelli/sec-edgar-mcp Primary language: Python GitHub stars: 378 GitHub description: A SEC EDGAR MCP (Model Context Protocol) Server README excerpt: A Model Context Protocol (MCP) server for accessing SEC EDGAR filings, financial statements, and insider trading data with exact numeric precision. Built on [sec-edgar-toolkit](https://github.com/stefanoamorelli/sec-edgar-toolkit).

Jupyter Notebook 380 stars

FrancescoSaverioZuppichini/Pytorch-how-and-when-to-use-Module-Sequential-ModuleList-and-ModuleDict

Code for my medium article

Overview: This project provides an overview of how to effectively use the three main building blocks of PyTorch: `Module`, `Sequential`, `ModuleList`, and `ModuleDict`. The article is based on a medium article and includes an example of a classic CNN classifier. Key features: - `Module`: The main building block of PyTorch, defining the base class for all neural networks. - `Sequential`: A container of Modules that can be stacked together and run at the same time. - `ModuleList`: A list of Modules that can be used to store and manipulate collections of modules. - `ModuleDict`: A dictionary of Modules that can be used to store and manipulate collections of modules. Tech stack: PyTorch Why it matters: This project is useful for developers who want to share, reuse, and break down the complexity of their models in PyTorch. It provides an effective way to write well-organized and organized code in PyTorch, which is often not as clear as the documentation suggests. Repository: FrancescoSaverioZuppichini/Pytorch-how-and-when-to-use-Module-Sequential-ModuleList-and-ModuleDict Primary language: Jupyter Notebook GitHub stars: 380 GitHub description: Code for my medium article

JavaScript 380 stars

anshaneja5/mldl.study

ML & DL roadmap with curated resources like videos, articles, research-papers, competitions, projects etc.

Overview: MLDL.Study is a comprehensive, free, and interactive learning platform for Machine Learning and Deep Learning, designed specifically for Indian audiences. It features curated resources, including videos, articles, and projects, to help users understand and develop their skills in these fields. Key features: - Interactive Roadmaps: Easy-to-follow paths for ML and DL concepts. - Diverse Resources: Video tutorials, articles, PDFs, and notes for each topic. - Community Growth: Over 10,000+ users. Tech stack: JavaScript. Why it matters: This platform offers a valuable resource for students and enthusiasts looking to learn Machine Learning and Deep Learning, making complex concepts accessible and engaging. Repository: anshaneja5/mldl.study Primary language: JavaScript GitHub stars: 380 GitHub description: ML & DL roadmap with curated resources like videos, articles, research-papers, competitions, projects etc. README excerpt: 🌐 MLDL.Study is a free and interactive learning platform designed for Machine Learning and Deep Learning education. It features curated roadmaps, videos, articles, and other learning materials. 🚀 Get started by cloning the repository and installing dependencies. 🚀 Project Structure: Content is organized into two main files, `categorizedMLContent.js` and `categorizedDLContent.js`, using simple JSON-like structures for contributions. 🛠️ Contributing: Add new resources, make changes, and create a Pull Request for approval. 📫 Contact: Reach out to the creator for any questions.

Python 380 stars

duoan/mega-data-factory

🏭 Mega Scale Multimodal DataPipeline for SOTA Foundation Models

### Overview: Mega Data Factory is a high-throughput, distributed open-source pipeline designed for processing web-scale multimodal datasets. Built on Ray with Rust-accelerated and GPU-optimized operators, it aims to support the reproducibility and scalability of state-of-the-art foundation models. ### Key Features: - **Text Data Pipelines**: Supports fine-tuning, quality filtering, and deduplication for large datasets. - **Image & Vision-Language Pipelines**: Implements image generation, quality filtering, and CLIP-based data curation. - **Video & Multimodal Pipelines**: Supports video captioning and video generation. ### Tech Stack: Rust-accelerated and GPU-optimized operators. ### Why it Matters: Mega Data Factory provides a robust, scalable solution for processing and managing large-scale multimodal datasets, enabling the development and evaluation of advanced foundation models. Repository: duoan/mega-data-factory Primary language: Python GitHub stars: 380 GitHub description: 🏭 Mega Scale Multimodal DataPipeline for SOTA Foundation Models

Python 380 stars

iLearn-Lab/NovelClaw

Dynamic-memory-first collaborative AI framework for long-form story generation, chapter planning, and coherent narrative writing

Overview: NovelClaw is a dynamic-memory-first collaborative AI framework designed for long-form story generation, chapter planning, and coherent narrative writing. It offers an inspectable writing workspace with sessions, storyboards, manuscript review, and memory-aware writing control. Key features: - Long-form fiction, serial writing, and chapter-by-chapter continuation. - Memory-aware drafting with inspectable chapter output and reusable story state. - Human-in-the-loop writing workflow. Tech stack: Python, FastAPI, Long-form fiction, Chapter control and memory. Why it matters: NovelClaw provides a structured workspace for long-form fiction work, making it easier to manage and review chapters, and offers a more direct control over chapter-level progress.

Python 380 stars

kpandey008/DiffuseVAE

Official implementation of "DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents"

Overview: DiffuseVAE is an innovative generative model that integrates a VAE within a diffusion model, offering improved quality and controllable synthesis capabilities. Key features: - Efficient and high-fidelity image generation - Controllable synthesis from low-dimensional latent representations - Better speed vs quality tradeoff compared to standard DDPM/DDIM models - State-of-the-art synthesis quality on benchmark datasets - Generalization to noisy conditioning signals Tech stack: Python Why it matters: DiffuseVAE combines the strengths of VAEs and diffusion models, offering improved quality, controllable synthesis, and a better speed vs quality tradeoff, making it a significant advancement in generative modeling.

JavaScript 380 stars

robotroutine/scriptum

No-Frills Functional Programming Lib Augmenting Javascript/Node.js

Overview: This library provides a lightweight, no-frills approach to natural language processing, focusing on string processing, regular expressions, and linear algebra. It adheres to functional programming principles, offering data structures such as balanced BSTs, lists, real-time queues, deques, and more. Key features: - String processing - Regular expressions - Linear algebra Tech stack: JavaScript Why it matters: This library simplifies natural language processing tasks by focusing on essential functionalities and leveraging functional programming, making it a valuable tool for developers looking to enhance their applications with robust yet concise NLP capabilities.

Python 380 stars

sign-language-translator/sign-language-translator

Python library & framework to build custom translators for the hearing-impaired and translate between Sign Language & Text using Artificial Intelligence.

Overview: Sign language is a method of communication used by the hearing-impaired, consisting of gestures and expressions. This project aims to bridge the communication gap between the hearing and the hearing-impaired community by utilizing Artificial Intelligence to translate between sign language and text. Key features: - Sign language translation API - Framework for building custom sign language translators Tech stack: Python Why it matters: This project aims to facilitate better communication between individuals with hearing impairments and the general population, making it easier for everyone to understand and interact with sign language. Repository: sign-language-translator/sign-language-translator GitHub stars: 377

Python 380 stars

zhizdev/sparsefusion

[CVPR 2023] SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction

### Overview: SparseFusion is a cutting-edge method that reconstructs 3D neural scene representations from as few as 2 input images, leveraging view-conditioned diffusion for enhanced accuracy and realism. ### Key features: - **View-conditioned Diffusion**: Uses diffusion models to generate consistent and realistic 3D reconstructions. - **SparseFusion Weights**: Pretrained weights for 10 categories, enabling efficient and accurate 3D reconstruction. - **Stable Diffusion VAE**: Compatible with Stable Diffusion V1.3 weights for enhanced image quality. ### Tech stack: Python ### Why it matters: SparseFusion offers a significant improvement in 3D reconstruction by combining view-conditioned diffusion with pretrained weights, resulting in more accurate and realistic 3D scenes from minimal input data. Repository: [zhizdev/sparsefusion](https://github.com/zhizdev/sparsefusion) GitHub stars: 380 GitHub description: [CVPR 2023] SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction