MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Founders OS - CRM, tasks, finances, feeds, and memory for founders, as an MCP server.
SkillMIT★ 21No key
A native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and delivers efficient AI coding assistance through hierarchical memory
SkillMIT★ 117No key
Gives VS Code agent mode planning superpowers with dynamic todo lists
SkillMIT★ 39No key
Deterministic, local, passive execution observer for AI agent workflows
Node.jsMIT★ 3Few starsNo key
The terminal office — an Ink TUI where a real agent manager (oikonomos) runs sub-agent employees: animated floor, mail, task board, chat with the boss.
SkillMIT★ 13No key
Automatic risk-based task routing and multi-agent orchestration for Codex using Sol, Terra, and Luna.
SkillMIT★ 4Few starsNo key
Local task-state ledger for AI coding agents. Preserve decisions, source conclusions, evidence, and checkpoints across Codex, Claude Code, Cursor, and other MCP clients.
Node.jsMIT★ 18No key
MCP server for vibe coding documentation - Auto-document your AI coding sessions
Node.jsMIT★ 1Few starsNo key
Spin up a personal, motivating daily focus board that renders in a browser canvas and that the user drives by talking to their AI partner. Tasks track status (to-do → in progress → done) with timestam
OfficialSkillMIT★ 40k in collectionNo key
One workbench for your AI coding projects - persistent plan/context/tasks across Claude Code, Codex, OpenCode, and VSCode Copilot Chat. Time tracking, dashboard, and autonomous execution for Claude Co
SkillMIT★ 4Few starsNo key
Integrate Microsoft Graph SDK into any project — .NET, TypeScript/JavaScript, or Python. Covers auth patterns (client credentials, OBO, managed identity), SDK setup, calling Graph APIs, batching, delt
OfficialSkillMIT★ 40k in collectionNo key
Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashb
PythonMIT★ 372No key
A notebook and ticket registry for agents: dated rows attached to a commit, a file, an item, an arc or the project, kept in a sibling git repo of JSONL.
SkillMIT★ 3Few starsNo key
Use this skill when the user needs to transform business requirements, use case descriptions, or meeting transcripts into a technical Power Platform solution architecture, including component selectio
OfficialSkillMIT★ 40k in collectionNo key
Agent skills that turn docs/ into an LLM-maintained wiki and task tracker. Obsidian-friendly. Works with Claude Code, Codex and Copilot CLI.
SkillMIT★ 23No key
Claude Code plugin for persistent AI memory. Store conclusions, not notes. OODA-driven reasoning artifacts with priority matrix, invalidation triggers, and seed activation.
SkillMIT★ 4Few starsNo key
A session-scoped memory layer for LLMs, built on the Model Context Protocol. LatentContext gives AI assistants the ability to explicitly store and retrieve notes, decisions, and context within a singl
Node.jsMIT★ 5No key
Use Firebase Authentication (Phone SMS OTP, Google, Email) with Better Auth sessions, organizations, and plugins. No Twilio needed for phone auth.
SkillMIT★ 19No key
Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.
SkillMIT★ 4.3kNo key
司南：个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents
SkillMIT★ 758No key
MCP server for Planora — connect AI assistants to your notes via the Model Context Protocol
Node.jsMITFew starsNo key
A git-native, review-gated knowledge base for AI agents: they propose writes, you approve them. Every claim cites a source, every change is a diff in your repo. MCP + CLI.
PythonMIT★ 72No key
The only Telegram skill your AI agent needs. Read messages, parse channels, download voice notes. User API via Telethon.
SkillMIT★ 8No key
Local MCP work notes with persistent sessions, decisions, evidence and resumable tasks.
PythonMIT★ 954No key
Who stands behind it
