python

A simple matrix bot that transcribes your voice to text message

Open-source AI assistant with voice control, browser automation, desktop overlay, and 109+ tools. Built with Python, Next.js, and Three.js.

Taught by AI genius Andrew NG, this course entails the cutting edge topics such as, How generative AI works including what it can and can't do, Common uses cases such as Reading, Writing, and Chatting, Life Cycle of GenAI projects, Advanced Technology options such as RAG, Fine tunning, and Pre-Training, Implications of GenAI on business & Society.

High-accuracy Russian ANPR system built with YOLOv8 for detection and an optimized, custom-trained PyTorch CRNN for OCR.

markdown parser and prompt generator tools for text2image prompts

In this dataset, the price of the dollar to the Iranian rial in the years 2011 to 2023 has been collected by our crawler.

PyGPTPrompt: A CLI tool that manages context windows for AI models, facilitating user interaction and data ingestion for optimized long-term memory and task automation.

An open-source platform that aggregates AI content from 230+ sources including research papers, GitHub trends, and industry news, making AI knowledge accessible to everyone.

CSVs of the Huggingface and LMArena LLM leaderboards, along with the code to generate them in Python and R.

Simple customizable evaluation for text retrieval performance of Sentence Transformers embedders on PDFs

Privacy-first document intelligence engine — parse PDFs, DOCX, PPTX, XLSX & CSV into AI-ready chunks for RAG pipelines. Includes HITL review, 3-layer memory chat, and a production FastAPI server.

YouTube MCP Server is an AI-powered solution designed to revolutionize your YouTube experience. It empowers users to search for YouTube videos, retrieve detailed transcripts, and perform semantic searches over video content—all without relying on the official API. By integrating with a vector database, this server streamlines content discovery.

Production-ready RAG framework for Python — multi-tenant chatbots with streaming, tool calling, agent mode (LangGraph), vector search (FAISS), and persistent MongoDB memory. Built on LangChain.

ML web service on FastAPI

A collection of Earth Engine Apps created using geemap and voila

Self-hosted multitenant platform for AI agents and Telegram bots with event-driven architecture

Full-stack LiveKit voice agent starter: a Python voice worker, FastAPI token server, and React frontend. Run, deploy, and swap each piece on its own. Ask for ShipVoice pro

VideoNote：视频链接 → 结构化笔记。理解画面/弹幕/评论；支持主流平台；工具解耦；多格式导出。

Convert images or audio files to plain text on the command line

基于 SenseVoice 的 Windows 本地语音转文字工具，支持 OpenAI 格式 API 润色，低延迟，高精度。