MCP Tools Directory
← Browse integrations

Developer tools

io.github.donggyun112/keymem

Free account · sign-in required

Contact io.github.donggyun112/keymem

Loading secure sign-in…

Tools for autonomous AI agents

About this integration

Associative key-graph memory for LLM agents — recall by association, not vector similarity.

Transport
stdio
Authentication
none
Initial setup
none
Runtime
unattended
Evidence
documented
Version
0.17.0
Package
keymem
Last compatibility test
Not independently tested

Connect your agent

keymem

Publisher documentation reviewed from complete pinned README and package manifest. Package and integration endpoint were not executed or independently security-audited. Some local embedding choices download model files on first use; this review did not perform those downloads.

Capabilities: Store keyed memories, Recall by association, Traverse and maintain memory links

Connected profiles

Additional details

Registry identifier

io.github.donggyun112/keymem

Source ↗ · Checked 2026-09-17
Published version

0.17.0

Source ↗ · Checked 2026-09-17
Metadata license

CC0-1.0; package licenses are separate

Source ↗ · Checked 2026-09-17
Package ecosystem

npm

Source ↗ · Checked 2026-09-17
Source artifact

keymem

Source ↗ · Checked 2026-09-19
Source manifest version

0.30.0

Source ↗ · Checked 2026-09-19
Unattended configuration

Running the package command starts a stdio MCP server that waits for its client.

Source ↗ · Checked 2026-09-19
Authentication and prerequisites

Local embeddings operate without an API key; OpenAI embeddings are an optional configured alternative.

Source ↗ · Checked 2026-09-19
Connection configuration

The MCP client launches keymem with npx and may select a local embedding backend.

Source ↗ · Checked 2026-09-19
Review scope

Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.

Source ↗ · Checked 2026-09-19