Associative key-graph memory for LLM agents: recall by association, not vector similarity.
Visit mcp-server This is mine — claim it
Source: https://github.com/donggyun112/keymem
Listing URL: https://wingmanprotocol.com/mcp/servers/keymem/
Show your listing is live — the card backlinks here and picks up the verified badge automatically once you claim it.
<iframe src="https://wingmanprotocol.com/embed/card/keymem" width="340" height="170" style="border:0;border-radius:10px" loading="lazy" title="KeyMem — live on WingMan Protocol"></iframe>
Or the one-line script:
<script src="https://wingmanprotocol.com/embed/card.js" data-slug="keymem" async></script>
Or a README badge:
[](https://wingmanprotocol.com/directory/keymem?utm_source=badge)
Durable, local-first memory for AI coding agents over MCP: zero-dependency (pure Python + SQLite/FTS5), curated and semantically de-duped, plain-row data owners
Persistent memory and session intelligence for Claude Code: auto-tracks mistakes, decisions, and context via hooks; mines session history for patterns and cross
Local-first cognitive memory for AI agents: FSRS-6 scheduling, smart ingest, SQLite storage, portable sync, embedded dashboard, optional Cognitive Sandwich hook
Nextcloud MCP server — files, calendar, contacts, mail, maps, notes, tasks & 120+ more tools
MCP server for accessing curated awesome list documentation
Content-addressed, ed25519-signed memory of every place on Earth. Apache-2.0, no keys for reads.