Browse and search the AI agent directory
323 agents found
Full - featured MCP implementation built with FastAPI and CockroachDB. Supports schema bootstrapping, JSONB storage, LLM-ready CLI, and optional `/debug` endpoints
Netlify runtime adapter for MCP servers built with ModelFetch
MCP Server for Browser Dev Tools
MCP server that runs Claude Code as tools — start coding agents, poll their progress, and control permissions from any MCP client
PostBot 3000 is an open-source project that shows how to build a powerful AI agent and stream responses and generate art
SwarmZero's SDK for building AI agents, swarms of agents and much more.
The open-source SDK for creating AI plugins and actions
MCP server package - managed by mcp-prep
🔬 Local SQLite-based AI research agent swarm with GOAP planning, multi-perspective analysis, long-horizon recursive framework, AgentDB self-learning, anti-hallucination controls, and MCP server. Goal-oriented with parallel execution. No cloud dependencie
MCP server for the OpSpawn x402 Bazaar — screenshot capture, AI analysis, PDF/HTML generation, code security scanning, and dependency auditing via x402 micropayments
A useful drawer for MacOS. chatting, clipboard, webscraping, window managing, shotcuts. built with Rust and ai-sdk
Agent Resource Discovery SDK — search tools, get reputation scores, auto-report usage
The Self-Coding System for Your App — Alan AI SDK for Web
MCP server package - managed by mcp-prep
Official TypeScript client & CLI for the Willi-Mako API v2 – OpenAI-compatible chat completions, streaming chat, EDIFACT analysis, market communication & ETL automation for German energy sector
Deno runtime adapter for MCP servers built with ModelFetch
Canonical npm package for the Safe Docx MCP server and CLI
W&B Traces enhances AI agent observability by providing intuitive visualizations for debugging LLMs, allowing practition
Node.js runtime adapter for MCP servers built with ModelFetch
A comprehensive package for searching the web and fetching web content programmatically, through a CLI interface, or through a Model Context Protocol (MCP) server.