Vana 的 Android 版（Compose）。iOS 版在 zjywill/Vana-iOS。

👩🏿‍💻👨🏾‍💻👩🏼‍💻👨🏽‍💻👩🏻‍💻中国独立开发者项目列表 -- 分享大家都在做什么

Fast, offline OCR for Node.js & C++. PP-OCRv6 with Core ML / WebGPU hardware acceleration — recognize text in images with confidence scores & coordinates. npm: @arcships/light-ocr

AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.

收集全网 Android TV电视盒子应用，涵盖影视、直播、K歌、工具、游戏等类型，整理优质APK资源，支持便捷下载与自动更新。提供安全验证、分类索引与兼容性标注，助力用户打造家庭影音娱乐中心！ ✅ TVBox/影视仓等影音壳接口配置源。

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

Pseudo Streaming SenseVoice with Hotwords

An extensive node suite for ComfyUI with over 210 new nodes

👨‍🏫 ChatTutor: Visual and Interactive AI Tutor

A Deep Learning Beginner: Nvidia's End to End Learning on Steering for Self-Driving Cars

A lightweight screen recorder based on ScreenCapture Kit for macOS / 基于 ScreenCapture Kit 的轻量化多功能 macOS 录屏工具

Un-LOCC: Universal Lossy Optical Context Compression for Vision-Based Language Models Achieve nearly 3x token compression at over 93% retrieval accuracy using existing Vision-Language Models.

Multilingual Document Layout Parsing in a Single Vision-Language Model

CLI tool for configuring and monitoring Claude Code

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

程序员延寿指南 | A programmer's guide to live longer

🎨 Python Echarts Plotting Library

所有小初高、大学PDF教材。

Ragflow-Plus 是 Ragflow 的二次开发版本，使其更为简洁实用

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Whisper STT + Orpheus TTS + Gemma 3 using LM Studio to create a virtual assistant.

Gemma3的comfyui版本

Website of the FUSE for macOS project

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.

macFUSE umbrella repository