Agentic AI
This repository serves as a comprehensive knowledge hub, curating cutting-edge research papers and developments across 24 specialized domains
What is Agentic AI?
Agentic AI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to this repository serves as a comprehensive knowledge hub, curating cutting-edge research papers and developments across 24 specialized domains
This repository serves as a comprehensive knowledge hub, curating cutting-edge research papers and developments across 24 specialized domains
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- This repository serves as a comprehensive knowledge hub, cur
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx agentic-aiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Agentic AI
The Agentic AI repository is a comprehensive, community-maintained knowledge hub that curates over 300 cutting-edge research papers, benchmarks, frameworks, and real-world system examples across 24 specialized domains of agentic and autonomous AI. It covers topics including multi-agent systems, AI safety, AI security, reasoning, evaluation benchmarks, foundation models, healthcare AI, and automation. Researchers, engineers, and practitioners use it as a structured index to stay current with the rapidly evolving agentic AI landscape, discover relevant papers by domain, and track developments across areas like AI evaluation methodology, robustness, and multi-agent coordination.
Prerequisites
- A GitHub account to browse, star, and contribute to the repository
- Git installed if you want to clone the repository locally
- An MCP-compatible client such as Claude Desktop if using the MCP server integration
- Node.js 18+ if running any associated TypeScript tooling
Browse the repository on GitHub
Navigate to https://github.com/mahmoudrabie/agentic-ai to explore the curated resource index organized across 24 domains. Each domain links to a dedicated markdown file with papers and resources.
Clone the repository for offline access
Clone the repository locally to read and search the curated knowledge base without an internet connection.
git clone https://github.com/mahmoudrabie/agentic-ai.git
cd agentic-aiExplore resources by domain
The repository is organized into 24 domain folders. Navigate into any domain directory to find research papers, benchmarks, and frameworks relevant to that area.
# Example domains:
ls agentic-ai/
# multi-agent-systems/
# ai-safety/
# ai-evaluation/
# reasoning/
# foundation-models/Install and configure as an MCP server
If an MCP server interface is provided for querying the knowledge base, add it to your MCP client configuration as shown below.
{
"mcpServers": {
"agentic-ai": {
"command": "npx",
"args": ["agentic-ai"]
}
}
}Contribute new papers or resources
The project welcomes community contributions. Fork the repository, add new papers or resources to the relevant domain markdown files, and submit a pull request to the main branch.
git fork https://github.com/mahmoudrabie/agentic-ai
# Add resources to the appropriate domain file, then:
git add .
git commit -m "Add new papers on multi-agent coordination"
git push origin mainAgentic AI Examples
Client configuration
MCP client configuration for connecting to the Agentic AI knowledge server if running as an MCP server.
{
"mcpServers": {
"agentic-ai": {
"command": "npx",
"args": ["agentic-ai"]
}
}
}Prompts to try
Prompts for querying the Agentic AI knowledge base through an AI assistant.
- "What are the most cited papers on multi-agent coordination in the agentic-ai repository?"
- "Summarize the key benchmarks used to evaluate autonomous AI agents"
- "Find papers about AI safety in the context of agentic systems"
- "What frameworks are available for building multi-agent AI systems?"
- "Show me recent research on LLM reasoning and chain-of-thought planning"
- "What real-world healthcare AI systems are documented in this knowledge base?"Troubleshooting Agentic AI
npx agentic-ai fails with package not found error
This repository is primarily a knowledge hub, not a published npm package. Clone the repository directly from https://github.com/mahmoudrabie/agentic-ai and browse it locally or via GitHub. Check the repository's README for the latest information on any available MCP server interface.
Cannot find papers on a specific topic
The repository is organized by domain folders. Use GitHub's search (press T on the repo page to search files, or use the search bar with repo:mahmoudrabie/agentic-ai <topic>) to find relevant content. You can also clone the repo and use grep or ripgrep locally: `rg 'your topic' agentic-ai/`
Frequently Asked Questions about Agentic AI
What is Agentic AI?
Agentic AI is a Model Context Protocol (MCP) server that this repository serves as a comprehensive knowledge hub, curating cutting-edge research papers and developments across 24 specialized domains It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Agentic AI?
Follow the installation instructions on the Agentic AI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Agentic AI?
Agentic AI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Agentic AI free to use?
Yes, Agentic AI is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Agentic AI Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Agentic AI? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Agentic AI in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Agentic AI?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.