Skip to content
mcp/skillhub

Mnema MCP Server

by zimac-aiai.zimac/mnemav0.2.0

Local-first, formally verified memory for AI agents: consult/learn/related/list over MCP.

0stdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Maintained3mo ago

Install Mnema MCP server

No published package or hosted endpoint yet — see the repository README for build-from-source instructions.

Configuration

VariableRequiredSecretDescription
MNEMA_DATA_DIR——Where the store lives (default ~/.mnema).
MNEMA_URL——Target store URL. Loopback (default http://127.0.0.1:7077) auto-starts a local daemon; a remote URL makes the server a pure authenticated bridge.
MNEMA_TOKEN—yesBearer credential when MNEMA_URL points at a token-protected remote store.

Freshness

Maintained — last maintenance signal 3mo ago. The newest of the signals below sets the band.

  1. Last commit (default branch)

    2026-07-12 · 3mo ago · GitHub

  2. Latest release

    2026-07-12 · 3mo ago · GitHub · v0.2.0

  3. Package published

    no data · npm/PyPI

  4. Registry entry updated

    2026-07-12 · 3mo ago · official registry · v0.2.0

FAQ

›Does Mnema require an API key?

Yes. It expects MNEMA_TOKEN, of which 1 is a secret.

›Can I use Mnema as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is Mnema in the official MCP registry?

Yes, as ai.zimac/mnema.

Alternatives to Mnema

Other memory MCP servers.

View all
MemoryActiveKnowledge graph-based persistent memory for maintaining context.HindsightActiveHindsight: long-term memory for AI agents modeled on human memory.Codebase MemoryActiveIndexes a repo into a persistent local knowledge graph of functions, classes, call chains, HTTP routes and cross-service links, using tree-sitter and LSP.CogneeActiveMemory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.HonchoActiveMemory that reasons: continual learning for stateful agents. Better context, fewer tokens.Basic MemoryActiveLocal-first AI memory: a semantic knowledge graph of Markdown files that humans and LLMs both read and write, with optional cloud sync and team workspaces.