MCP server · Research

AI Open Source Intelligence

Lets your AI search a live radar of open-source AI projects, compare them, and plan a stack for you.

Research For it and development Research

This is a helper that lets your AI look up open-source AI projects on a live radar, check facts about them, and compare a few side by side. It is handy if you are trying to choose tools for a project and want answers backed by real sources instead of guesses. You do not need to be a developer to use it, you just ask questions in plain words.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you using what it already knows. An MCP server is a small helper program that gives your AI a new skill or a connection to a service. This one connects your AI to the AI Open Source Radar, a public collection of open-source AI projects. Once it is connected, your AI can look things up there and bring the results back into your chat when you ask.

What this MCP server does

You ask your AI something like which open-source chatbot projects have a web interface and a friendly license. Your AI uses this helper to search the public radar and pull project details. The helper talks to the radar, gathers facts and license evidence, and hands them back to your AI. Your AI then writes the answer for you, keeping verified facts, its own suggestions, unknowns and risks in separate groups. Everything it does is read-only, so it never installs or runs anyone else's code.

Flow diagram: you ask your AI “Find open source AI chat projects I can host myself”, the AI Open Source Intelligence connects it to AI project radar, and you get back project lists and comparisons.

Click to zoom

What you can do with it

Search a live radar of open-source AI projects by what you need
Check the facts and license evidence for a named project
Compare two to five projects for one specific use case
Find alternatives to a project while keeping your must-haves
Plan a candidate open-source AI stack and flag what is unverified
Browse radar rankings, categories, scenarios and skills

Try asking your AI

“Find open-source AI chat projects with a web interface that I can self-host and that have a permissive license”
“Compare these three projects for a small team with no budget and no cloud”
“What do we actually know about this project's license, and what is still unverified”
“Suggest an open-source stack for a document question answering tool, and tell me which parts are not confirmed to work together”

What it gives back to you

You get answers in your chat, not files. They come as lists of projects, short fact sheets, side-by-side comparisons, and a stack plan. Each result is split into verified facts, recommendations, unknowns and risks, so you can see what is solid and what is not. License information is shown as an observed label until a real license file backs it up.

Before you start

What you need

An AI app that supports MCP servers, such as the ChatGPT desktop Codex host or Codex
For ChatGPT web: add the server as a developer-mode app with No Authentication
For a local Python setup: Python 3.10 or newer and the package from PyPI

Good to know

It only reads public radar data and never installs or runs anyone else's code, but license information is technical evidence and not legal advice, so check with your own team before relying on it.

Install it with your AI

Add AI Open Source Intelligence to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check AI Open Source Intelligence, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.