Lists (2)
Starred repositories
Fully offline voice assistant on ESP32-S3 (Freenove FNK0104B): free-form STT, tiny LLM, TTS https://iamankushpandit.github.io/esp_ai/
ComfyUI 中文人体姿势图库节点，支持多视角浏览与 Depth Anything → MOSS SFT 深度控制工作流
A multi-platform proxy client based on ClashMeta,simple and easy to use, open-source and ad-free.
Robot and controller code for a replica robot
1407 张 AI 女装参考图集与虚拟试穿网站，支持中英检索、OpenAI Images / Gemini / 豆包及自定义 Base URL、API Key、模型。https://github.com/paipiange/nvzhuang
Build and run agents you can see, understand and trust.
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and supp…
A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.
Open-source, self-hosted alerting for metrics, logs, and databases. Includes a built-in AI agent and MCP server.
姿势、服装、人像参考图库，附中英文提示词，可在浏览器里 AI 试穿 · Pose, outfit & portrait reference library with bilingual prompts and in-browser AI try-on
发布前审｜发抖音/小红书/视频号前先让 AI 审一遍：哪句踩线、依据哪条官方规则、给能直接用的改法。38 篇真实样本校准判定尺度，80+ 条官方原文引文可查证，你踩过的坑沉淀成本地规则库越用越准。不承诺过审，不教绕审。
Smaller images, same picture. Compress PNGs to PNG or WebP with automatic quality. PNG output is 8–12% smaller than TinyPNG at equal quality on the median image. Command line and browser.
A smarter, self-hosted AI assistant — multi-user, multi-agent.
Reverse engineer anything with agents, from app behavior down to native binaries.
Arduino core for the ESP32 family of SoCs
ESP-Claw, a "Chat Coding" AI agent framework for IoT devices
Emulate Arduino, ESP32 & Raspberry Pi. in your browser. Write code, compile, and run on 19 real boards — Arduino Uno, ESP32, ESP32-C3, Raspberry Pi Pico, Raspberry Pi 3, and more. No hardware, no c…
Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak.
一键批量下载豆包/Dola无水印图片/视频资源、强制生成15秒视频的浏览器扩展/油猴脚本。
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
CUBOTino base version: a Small, Simple, 3D Printed, Inexpensive Rubik's Cube Solver Robot
A framework-agnostic embedded file viewer for vanilla JavaScript, React, Vue and Svelte. Put PDF, Office, images, media, archives, email, drawings, 3D, GIS and engineering files inside one stable c…
RL training environments for Microduck (mjlab)
拖入项目，生成 60 页软著源程序文档。离线抽取、注释清洗、自动排版，导出前先帮你过一遍审查——代码不出本机。