Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Relevance-gated, self-improving procedural memory for AI agents, as an MCP server. Loads only the lessons relevant to the task, learns from failures, prunes what it never uses. ~99% less context per t
PythonMITFew starsNo key
Read-only MCP server for WaniKani: query your reviews, lessons, assignments, review stats and study notes through the official API v2. Local stdio, TypeScript.
Node.jsMITFew starsNeeds a key
🌑 SAKU (朔) — A self-evolving local AI agent with persistent personality and Markdown memory
PythonMIT★ 2Few starsNo key
Personal agent orchestration platform: SQLite task queue + tmux/worktree Claude Code workers, scheduler, adversarial review
SkillMIT★ 9No key
Hi AI Tutor turns a PDF, notes, or a topic into an interactive lesson with narrated slides, quizzes, simulations, sharing, and plan-dependent exports.
SkillMITFew starsNo key
Faroz kids' learning platform: courses, lessons, exercises, homework, calendar and strategies.
Hosted by authorNo licenseFew starsNo key
A persistent personal assistant that wakes on a schedule it picks, keeps its own notes, and brings things up on its own. Kin to Lobo; standard-library Python.
SkillMIT★ 4Few starsNo key
Local memory layer for AI coding hosts (Cursor, etc.). Distills conventions, prohibitions, and repair lessons verified in conversations, injects them as reviewed rules, and recalls them before the nex
PythonMITFew starsNo key
Transform Claude Code into an organized command center — session persistence, daily task tracking, multi-domain routing, interactive onboarding. Production-tested template.
SkillMIT★ 1Few starsNo key
Your AI chief of staff: persistent memory, task management, meeting notes, MCP integrations, daily Slack briefings, and a self-improving agent that gets smarter over time. Built on plain markdown, run
SkillMITFew starsNo key
🧠 Git-native persistent memory & task graph for AI coding agents (Claude Code, Cursor, Antigravity). The lightweight TypeScript MCP alternative to Beads.
Node.jsMITFew starsNo key
Persistent memory for Claude Code — notes, episodic, and procedural memory across sessions (MCP + hooks).
PythonMITFew starsNo key
The Learning Path Generator is a Streamlit-based AI application that uses the Model Context Protocol (MCP) to create personalized learning journeys. It integrates with YouTube for video lessons, Googl
MCPLink onlyFew stars
Your work, already underway. A personal AI assistant for your job: mail, chats and tickets become tasks, the agents you already use (Claude Code, Codex, Gemini) do the work, and nothing goes out until
PythonMIT★ 143No key
MCP server that builds a personal course: learner profile, keyless research with sources, evidence-based roadmap, schedule, and export to Aurora Slides
Node.jsMIT★ 4Few starsNo key
Local-first continuity layer for AI coding agents: move a task between Claude Code, Codex, Copilot, Cursor and others without losing its state. CLI, MCP server, worktrees and headless ACP runs.
SkillApache-2.0★ 5No key
Plans every prompt into a spec + Graph of Thought, tracks it in Linear/Notion, and ships finished work through a Greptile-gated PR. One plugin for Claude Code, Grok Build, Hermes Agent, Muse and Omp.
SkillAGPL-3.0★ 1Few starsNo key
A swarm-style multi-agent system where stateless agents collaborate via a shared task board.
SkillApache-2.0★ 5No key
Who stands behind it