MCP servers and skills: search, filter by where they run, and compare.
Redis cache handler for Next.js 16 — supports both cacheHandler (ISR) & cacheHandlers ('use cache'). Lua-atomic tagging, in-memory fallback, deploy isolation
Node.jsMIT★ 6Needs a key
Production-ready Next.js template for building AI agents with LangGraph.js. Features MCP integration for dynamic tool loading, human-in-the-loop tool approval, persistent conversation memory with Post
SkillMIT★ 134No key
Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes.
SkillMIT★ 6.4kNo key
Open-source AI sales OS — self-hosted CRM with native AI agents + WhatsApp (WAHA). Open alternative to Kommo, Octadesk & Intercom for any business that sells by chat. MCP-ready, multi-tenant, LGPD.
SkillMIT★ 4.6kNo key
AI-powered StartUp Accelerator Engine built with Next.js, LangChain, PostgreSQL + pgvector. Upload, organize, and chat with documents. Includes predictive missing-document detection, role-based workfl
SkillApache-2.0★ 894No key
Open-source, self-hostable platform for building and operating AI phone agents.
SkillMIT★ 493No key
The skill layer for AI agents: npm for AI Agent Skills.
SkillMIT★ 361No key
🔥 Lightweight, Airbrake/Sentry-compatible, PostgreSQL-based Open Source Error Catcher
SkillMIT★ 220No key
A Pokémon-style adventure built with Codex, featuring AI-generated maps, NPCs, branching saves, and multiplayer. The adventure never ends.
SkillMIT★ 184No key
Open-source AI Search Intelligence Platform — track, analyze, and improve AI visibility, citations, prompts, competitors, and content opportunities across ChatGPT, Claude, Gemini, Google AI Overviews,
SkillMIT★ 142No key
Opinionated agent skills for shipping production apps on Next.js, FastAPI, PostgreSQL, Expo, and SwiftUI.
SkillMIT★ 4Few starsNo key
A production-grade portfolio template with a real backend, an AI agent API, and a motion engine that measures animation instead of guessing. One config file to make it yours. Next.js 16, React 19, Tai
SkillMIT★ 17No key
A dating platform built for AI agents. Register, swipe, match, chat, and form relationships via API.
Node.jsMIT★ 26No key
Open-source multi-tenant LMS for creators and schools: sell courses on your own subdomain. Next.js 16 + React 19 + Supabase (RLS) + Stripe Connect, an AI tutor over MCP, gamification, certificates, i1
SkillMIT★ 39No key
Open source LLM observability and monitoring. Drop-in proxy for OpenAI, Anthropic, and Gemini with request logging, cost tracking, and agent tracing. Self-host with one Docker command. MIT.
Node.jsMIT★ 13Needs a key
Adaptive memory for AI agents & teams — beyond RAG. Self-hosted MCP server that gets smarter every time you search: hybrid search + a neural memory graph that learns. Works with Claude, ChatGPT & any
Hosted by authorApache-2.0★ 12No key
Claude Code 플러그인 — 웹사이트 SEO/GEO 진단(크롤·렌더·CWV·구조화데이터·AI크롤러정책·회귀감지) + GSC/GA4/PSI 연동. Next.js 프로젝트 승인 기반 자동수정(canonical·OG·noindex·robots·JSON-LD·제목·메타설명) + GitHub 저장소 PR 제안(실험적)
SkillApache-2.0★ 16No key
Stop saying "wait, I had the perfect meme for this." Save your favorites, build shareable playlists, and become the meme lord your group chat deserves.
SkillMIT★ 19No key
A free kanban board you can share with a link. No account, no email, no install — name a board, set a password, send the link, and everyone drags the same cards.
Hosted by authorMIT★ 11No key
An operator desk for self-updating agent skills. track sources, refresh with agents, version every change. Built with Vercel AI Gateway + Sandboxes + Queues.
SkillMIT★ 18No key
A PaaS you run on your own server. docker push, and it is live — with HTTPS, a database beside it, and a second machine when one stops being enough.
SkillApache-2.0★ 17No key
You say the job; the playbook runs. 161 agent skills + 63 slash commands for Claude Code, Cursor, Codex, and Gemini CLI. Tuned for React / Next.js / Supabase.
SkillMIT★ 8No key
SigRank SignalAF — AI operator evaluation leaderboard. Ranks how efficiently you use AI by token cascade efficiency (Υ = cache_read × output / input²). Privacy-preserving: token counts only, never pro
Hosted by authorMIT★ 6No key
Who stands behind it
