AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

Scrape JavaScript-heavy sites and extract structured data via reusable CSS schemas. Portable agent skill wrapping the Crawl4AI CLI and Python SDK.

The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

Transparent and Efficient Financial Analysis

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

MCP Server for Facebook ADs Library - Get instant answers from FB's ad library

A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

Open-source AI assistant ecosystem with MCP integrations, multimodal workflows, IoT support, and cross-platform voice interaction.

Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

Product-Led Growth (PLG) analysis toolkit that detects tech stacks, plans growth loops and builds the loop iteratively.

MCP server that gives agents Yahoo Finance data and charts.

368 AI skills, 76 expert agents, and 859 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, and research. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.

Extract public Spotify data — tracks, albums, artists, playlists, podcasts & lyrics — without the official API. Sync + async, typed models, one dependency.

MCP server retrieving transcripts of YouTube videos

Experiment task scheduling made easy.

PDF RAG server for cursor.

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

This project provides an Interactive Brokers (IB) API interface using the Model Context Protocol (MCP).

pentestMCP: AI-Powered Penetration Testing via MCP, an MCP designed for penetration testers.

Academia MCP server: Tools for automatic scientific research

Compound Engineering Framework for Alpha Feature Research in Quant Finance