theskillcity
API KeyMarkdownProject ModeMarket SkillsDocsWorkspace

Discover the toolingbehind modern intelligence

The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.

 
 
In active build — expect changes
Indexing Status

Find your way around

© 2026 theskillcity · Independent open-source indexBuilt in public · v0 beta
theskillcity

Discover the toolingbehind modern intelligence

A live, classified map of MCP servers, AI agents, LLM tooling, automation systems, and developer infrastructure — searchable in one place.

⌘K
TrendingRecent

FAQ

Frequently asked questions

A live, classified index of the open-source tooling behind modern AI — MCP servers, AI agents, LLM tooling, automation systems, skills and developer infrastructure — all searchable and mapped in one place. The homepage cityscape lets you explore by category; everything else is a click away.

0skills
0MCP servers
0agents

Browse by domain — interactive skyline. Each building links to a domain.

DEVTOOLSLLMAGENTSAUTOMATIONWORKCLOUDWRITINGSECURITYWEB/APPMEDIADATA/ML
10All domains

Creative, Vision & Voice

10

Image, video, audio — generation, transcription, downloaders, players, recorders.

Specializations

AllAudio & Speech138 reposImage Generation81 reposVideo77 reposDownloaders & Players18 reposVision & Recognition10 repos
0specializations
0repos
0skills
0MCP servers
0agents
Jennyee1

AcademicAgent

Jennyee1
SKILL

ScholarMind - 面向大模型Agent领域的多模态学术 Agent | Multimodal Academic Research Agent with Knowledge Graph & Learning Path Planning

Creative, Vision & Voice
3363Python
gca-americas

way-back-home

gca-americas
MCP

🚀 Way Back Home

Creative, Vision & Voice#a2a#adk
7649Python
mario-andreschak

mcp-image-recognition

mario-andreschak
MCP

An MCP server that provides image recognition 👀 capabilities using Anthropic and OpenAI vision APIs

Creative, Vision & Voice
3910Python
Mriestac

mimo-image-recognition-mcp

Mriestac
MCP

No description provided.

Creative, Vision & Voice
190Python
fabriqaai

ffmpeg-analyse-video-skill

fabriqaai
SKILL

Claude Code skill: analyse video content by extracting frames with ffmpeg and using AI vision to generate timestamped summaries

Creative, Vision & Voice
101
jfcrary

OpenClaw-Neuropath-Skills

jfcrary
SKILL

Training specialized OpenClaw agents for neuropathology WSI analysis with modular expert skills for neuroanatomy, lesion interpretation, tauopathy staging, and multimodal reasoning. Also encoding foundational scientific method frameworks inspired by Cajal, Alzheimer, and other giants of observational neuroscience into

Creative, Vision & Voice
22
AlexiosBluffMara

mercury

AlexiosBluffMara
SKILL

Mercury — Gemma 4 multimodal AI agent for the Digital Equity track. Local-first, $0/month on consumer hardware. Dual-targeted to Gemma 4 Good Hackathon (Kaggle × Google DeepMind, May 18 2026) and the Nous Research Mercury Creative Hackathon. Apache 2.0.

Creative, Vision & Voice
20Python
jabbertones-cloud

blender-mcp

jabbertones-cloud
MCP

OpenClaw Blender MCP - 65+ FastMCP tools, TCP bpy bridge, multi-instance ports (9876–9885), 3D Forge pipeline, product animation presets, render QA.

Automation & Workflows#automation#blender
11Python
sjkncs

UI-TARS-desktop

sjkncs
MCP

🤖 Community fork of ByteDance UI-TARS-desktop | Multimodal AI Agent with Chat System, Message Actions, Global Shortcuts & Optimization Settings | 基于字节跳动 UI-TARS-desktop 的社区增强版，新增聊天系统、消息操作栏、全局快捷键与优化设置

Creative, Vision & Voice#agent#coworking
10TypeScript
glasses666

mcp-image-recognition-py

glasses666
MCP

MCP Server for Image Recognition using Python and multiple LLM providers

Creative, Vision & Voice
10Python