基于视觉原语范式的多模态视觉理解 MCP 服务器。通过任务调度机制，将场景理解和坐标定位分离为独立工具，实现「先看清 → 再定位」的精确空间推理。

"We can wander through the stacks of the Library of Alexandria, imagining the scrolls and the knowledge they contain. Its destruction is a warning: all we have is transient.”--Alberto Manguel

ClawdHome securely isolates and manages multiple OpenClaw gateway instances on one Mac.

Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.

Make Any Website into CLI & Use your logged-in browser by AI agent.

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

Bring Claude's Skills pattern to any agent

【技术文章配图大师】一个为技术媒体人设计的 Claude Skill，让 AI 配图告别"塑料感"。

Agents that use the browser.

A Model Context Protocol server for Excel file manipulation

Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组

Create Magic Story!

FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

Android real-time display control software

A libre lightweight streaming front-end for Android.

Instant voice cloning by MIT and MyShell. Audio foundation model.

使用 express 和 vue3 搭建的 ChartGPT 演示网页

Project flat is the Web, Windows and macOS client of Agora Flat open source classroom.

A new handy and powerful Android phone assistant， powered by Flutter.