Browse the library

This plug-and-play library enables AI agents to call MCP and UTCP tools more efficiently via code execution, reducing costs and iterations.

This token-efficient MCP adapter enhances the Pi coding agent's interaction with MCP servers, saving tokens and managing server instances dynamically.

Keeps specialist agents in a hub and spins up a temporary orchestrator per task, running inside Claude Code, Codex, Cursor and Gemini.

Prismer Cloud is an intelligence runtime that provides AI agents with features like collaboration, persistent memory, error recovery, and shared learning.

A port of Poteto's pstack skill stack for Claude Code and other agents, providing rigorous agent workflows for improved outcomes.

Records and transcribes meetings and voice memos on-device into Markdown, which Claude Code, Cursor or any MCP client can then search.

This MCP server provides agents with deep codebase understanding, git history, and web research for contextualized software development.

This is an automated index listing over 43,000 Claude Code plugins, their descriptions, and adoption metrics for discovery.

Claude Code plugin bundling specialized agents, skills, hooks and mode commands, installable with one npx command and compatible with Cursor, Codex and more.

Octogent is an orchestration dashboard for Claude Code, managing context, automating tasks, and enabling multi-agent coordination.

A CLI that uses YAML to define repeatable multi-step workflows for AI coding agents with isolated environments.

This orchestrator allows AI coding agents like Claude Code and Cursor CLI to work together in parallel or sequence within isolated tmux sessions.

Heym is a self-hosted platform for building, orchestrating, running, and controlling agentic systems, integrating agents, tools, and MCP on your infrastructure.

This plugin enables natural voice conversations with Claude Code and other MCP-capable agents, allowing hands-free interaction.

nocturne_memory

Dataojitori

This MCP server provides rollbackable, graph-like long-term memory for AI agents, allowing them to remember context across sessions and models.

This plugin captures, indexes, and makes AI development conversations searchable and shareable, creating reusable skills from chat history.

A skills pack or full harness that verifies agent work with stop-hook gates, artifact checks and independent judges across Claude Code, Cursor and Codex.

Provides ADHD-friendly output styles for Claude Code and similar AI agents to make their responses concise, easy to skim, and human-readable.

Provides a self-hosted MCP gateway to manage and consolidate multiple MCP servers, offering a single endpoint for AI clients and agents.

Syncs AI agent configurations, skills, and context files across Claude Code, Cursor, and Codex, with continuous context refresh and compaction features.

A coding-agent skill that improves reliability in agentic coding tasks by reviewing, fixing, and rechecking agent work to cut failures.

A shared knowledge layer for AI agents to persist and query collective learning to avoid repeating mistakes.

This MCP server and CLI tool prevents AI agents from hallucinating by verifying every claim against ground truth with evidence, preserving context across sessions.

Agent skills and an AGENTS.md template for worktree isolation, service-layer structure, evidence-based testing and before/after screenshots in PRs.