What it does
The publisher describes Memory for AI as a local knowledge graph of a codebase, built for use by AI agents. The publisher states that it covers 162 languages, that queries complete in under a millisecond, and that it reduces token usage by 99%.
The publisher's description does not detail specific use cases. It is relevant to work where an AI agent needs structured knowledge of a codebase.
The source is hosted on GitHub under the publisher's repository. The description does not list installation or setup steps.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Memory for AI
Local codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
v0.11.0As shown on registry.modelcontextprotocol.io when we last read it