Browse the library

An open-source CLI agent that provides direct terminal access to Gemini's AI capabilities, including search, file operations, and shell commands, with MCP support.

This self-hosted Python framework enables building personal AI agents with a WebUI, tools, memory, MCP integrations, and multi-agent workflows.

codebase-memory-mcp

DeusData

This MCP server provides high-performance code intelligence to AI agents by indexing codebases into a knowledge graph for faster, token-efficient queries.

Lets your AI agent interact with graphical user interfaces, browsers, and your computer through a multimodal agent stack.

claude-code-router

musistudio

Offers a local control plane to route, orchestrate, and observe requests across multiple AI agents and models from one application.

A command-line interface for the open agent skills ecosystem, enabling easy installation and usage of skills across various AI coding agents.

An MCP server that acts as an IDE for coding agents, providing semantic code retrieval, editing, refactoring, and debugging tools to improve agent efficiency and reliability in complex codebases.

The official Python SDK for Model Context Protocol (MCP), enabling developers to build custom MCP servers and clients to extend AI agent capabilities.

A local proxy to use any LLM like Gemini, DeepSeek, or Ollama with agents like Claude Code and Cursor.

An open-source platform for building and deploying durable AI agents and workflows in TypeScript, featuring long-running tasks, retries, and queues.

ccstatusline

sirmalloc

Add a customizable status line to Claude Code CLI displaying model info, Git status, and token usage.

This agentic workspace allows AI agents to interact with over 100 integrations, local files, and apps with shared memory, operating locally for full data control.

Install and manage Anthropic-style SKILL.md plugins across multiple AI coding agents like Cursor and Aider.

An MCP server that optimizes agent context, reducing token costs and improving accuracy through codebase mapping.

This framework helps build effective and robust AI agents using the Model Context Protocol, offering full MCP support and composable agent patterns.

A curated collection of MCP (Model Context Protocol) resources, clients, and servers, with guides for Chinese users to leverage AI agent capabilities.

Reduce Claude Code token usage by rendering bulky text context into compact images for the model to process.

A community-driven directory to discover and install Model Context Protocol (MCP) servers into your AI tools.

Connects the ChatGPT web app to Codex via a read-only MCP, allowing ChatGPT to act as the planning and review brain for Codex coding sessions.

This tool enables AI agents to perform fast and accurate code search in natural language, significantly reducing token usage.

OpenAgent is an open-source personal AI assistant that combines LLMs, RAG, and agent loops, enabling it to browse the web, run code, and use any MCP-compatible tool.

code-graph-rag

vitali87

Allows AI agents to query, understand, and edit multi-language codebases using a knowledge graph built from code structure.

This Ghidra MCP server provides over 200 tools for AI-powered reverse engineering, offering full read/write access to binaries and supporting complex analysis workflows.

Acts as an AI gateway, registry, and proxy to unify and manage various AI agents, tools, and APIs, optimizing agent workflows and supporting plugins.