mozg MCP server

mozg.

Knowledge with an owner, a score, and a meter. Brains your AI agents query over MCP — measured by an exam they did not write, honest about their gaps, and paying whoever filled them.

Manifesto · Start here · Catalogue · Status · Self-host · Roadmap

We are building one memory for the whole species. Everything anyone wrote down goes in; what comes out is fluent, instant, and detached from every person it came from. Three things follow from that shape, and none of them is a bug:

• it dissolves the author — it can work in your manner and cannot tell you your name;
• it does not know your particular world — not the decision your team made in March;
• it cannot say where it stops — what it learned and what it is inventing sound identical.

It knows what we know.

It cannot tell you who taught it.

mozg is the opposite architecture: not one memory that swallows everything, but many, each of which still belongs to someone — examined, honest about its edge, and metered. One mechanism holds it together:

Knowledge must be measured.

The loop

flowchart LR
    A[one docs URL] --> B[crawler<br/>github tree · llms.txt · sitemap]
    B --> C[atomic notes<br/>+ embeddings]
    C --> D{{the exam<br/>~30 questions from the goal}}
    D -->|score + failed questions| E[focused re-read<br/>chases the gaps]
    E --> C
    F[agents querying over MCP] -->|zero-hit searches| D
    F -->|corrections| G[owner review] --> C
    F -->|proposals from readers| G

Shortened. The full README is on GitHub.