MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Turn raw community conversations into validated customer intelligence using a three-stage Claude Skill reasoning pipeline.
SkillMIT★ 2Few starsNo key
Hop across your ChatGPT threads from Claude Code. Fan out one question to many conversations, harvest every angle, synthesize the pattern between them.
SkillMITFew starsNo key
Web-based 3D & physical simulation development, rendering, and validation toolkit for AI agents.
SkillMITFew starsNo key
Forgewisp — safe, function-calling AI agents for the browser. Register your own functions as validated tools, with risk-tier execution, OpenAI-compatible streaming, dual reasoning streams, and an audi
SkillMIT★ 4Few starsNo key
Agent Skill that teaches Cursor & Claude Code to output single-file HTML for spatial, parallel, comparable, or interactive content. 9 categories, 20 patterns, 12 ready-to-use templates. Inspired by Th
SkillMIT★ 7No key
High-performance data primitives for browser visualization — Rust/WASM downsampling, binning, spatial indexing, streaming aggregation, with an MCP server
SkillMIT★ 2Few starsNo key
把 Google Gemini 网页端反代成 OpenAI 兼容 API 的浏览器登录拓展版 —— 在原项目基础上新增全自动 Cookie 供给链路（浏览器登录抓取 / 有效期自动保活 / 失效才刷新 / 抓取后模型校验）。
GoMIT★ 6No key
A tool-first AI agent harness for durable repository work across terminal, browser, ACP, LSP, and CI.
GoMIT★ 9No key
A skill to be able to use codex headless in any harness.
SkillMITFew starsNo key
Headless product design for AI coding agents, backed by a transactional product graph | Design how it works, verify what you ship.
SkillApache-2.0★ 120No key
DeepSeek-native local AI agent workspace for Mac, Chrome, Android, MCP, browser automation, long-context coding, and private multi-device workflows.
SkillMIT★ 7No key
An agentic AI that improves merchant performance through an Observe, Diagnose, Decide, Act loop, analyzing key signals to compute KPIs, detect bottlenecks, and generate high‑impact actions like pricin
SkillApache-2.0Few starsNo key
ego lite skill — each DOM step decided in ~0.4s, no LLM turn
SkillMIT★ 15No key
High-performance MCP server for browser automation, web capture, and content extraction. Rust-powered CDP client for AI agents.
SkillApache-2.0★ 3Few starsNo key
Arcgram — an interactive diagram engine for human–AI collaboration: an AI agent draws its reasoning as an auditable node-and-edge flow and self-audits it, delivered as one standalone HTML file. (Arcgr
SkillApache-2.0★ 13No key
High-reasoning Claude Code orchestration skill with guarded PLAN-BUILD-JUDGE contracts and optional Cursor headless acceleration
SkillMIT★ 4Few starsNo key
ART is a powerful, modular, and browser-first JavaScript/TypeScript framework for building sophisticated LLM-powered intelligent agents capable of complex reasoning, planning, and tool usage.
SkillMIT★ 2Few starsNo key
Browser-based RDF/ontology knowledge graph editor — load RDF from files, URLs or SPARQL endpoints; author nodes and edges on the canvas; run OWL-RL reasoning; apply multi-algorithm layout and clusteri
MCPLink only★ 253
Local-first MCP client studio: LangGraph ReAct agent + OpenAI-compatible /v1/chat/completions backend + React Studio UI with reasoning rail. DeepWiki/Fetch/Time MCPs by default. Ollama on AMD ROCm.
SkillMITFew starsNo key
Export opencode AI coding sessions to beautiful HTML + JSON archives. CLI + MCP server with secret redaction.
PythonMIT★ 2Few starsNo key
Token-efficient browser automation MCP for AI agents, with semantic page snapshots and stable element IDs.
Node.jsMIT★ 18No key
An evidence-first data analysis skill for Excel/CSV with ReAct reasoning, deterministic harness audit, and executive HTML dashboards (Case study: Kaggle EV Adoption benchmark)
SkillMIT★ 1Few starsNo key
A spec‑driven readiness system using simulation, diagnostics, and agentic AI to produce explainable insights. Outputs include rule paths and RS256‑signed records. It models workload and risk to score
SkillApache-2.0★ 1Few starsNo key
Who stands behind it
