1. Conduid
  2. RAG
  3. Engraphy
MCP server · RAG

Engraphy

by · github.com/devon-clarkk/engraphy

An MCP server giving AI agents associative memory, modelled on the human mind. The name comes from engraphy, the old memory-science term for laying down an engram, the trace a memory leaves in the brain. Self-hosted: typed graph on Postgres and pgvector. Source-available under BSL 1.1.

Unclaimed ai-agent-memoryai-agentsknowledge-graphllmmcpmcp-servermemorymodel-context-protocolpgvectorpostgrespythonragself-hostedvector-search
InstallView source
34Low

Scored a month ago · breakdown

About Engraphy

Engraphy is an MCP server published by devon-clarkk in the RAG category: an MCP server giving AI agents associative memory, modelled on the human mind. The name comes from engraphy, the old memory-science term for laying down an engram, the trace a memory leaves in the brain. Self-hosted: typed graph on Postgres and pgvector. Source-available under BSL 1.1.

Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/devon-clarkk/engraphy

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (7)

admin_*Space administration (members, tokens, grants, visibility).

Parameters not published.

briefingPack-declared session-start sections (due commitments, relevant notes, …).

Parameters not published.

getFull nodes plus edge summaries, by id.

Parameters not published.

scope_guideThe routing manifest: every writable scope and what it governs.

Parameters not published.

searchHybrid semantic + lexical retrieval across one scope or all.

Parameters not published.

traverseRecursive graph walk from a starting node.

Parameters not published.

writeDedup-banded write; returns the node or a duplicate-check verdict plus a resonance report.

Parameters not published.

Ask AI

✦

Ask AI about Engraphy

Powered by Claude · Grounded in docs

I know everything about Engraphy. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v0.3.0Engraphy v0.3.0 · 18 Sep 2026Engraphy 0.3.0 stores a memory that carries a partial or imprecise date, and it scores level with Mem0 on LoCoMo. Memory writes A `date` attribute accepts a full ISO date (`2026-01-15`), a year and month (`2026-01`), or a year (`2026`).…
v0.2.0Engraphy v0.2.0 · 24 Aug 2026What's Changed Engraphy 0.2.0: the default embedder runs on ONNX Runtime by @devon-clarkk in https://github.com/devon-clarkk/engraphy/pull/1 New Contributors @devon-clarkk made their first contribution in…
v0.1.0Engraphy v0.1.0 · 22 Aug 2026Engraphy is a self-hosted memory engine for AI agents. It stores what an agent learns as a typed knowledge graph on Postgres + pgvector, and speaks the Model Context Protocol, so any MCP client (a VS Code extension, a desktop app,…
Questions

About Engraphy

How do I install Engraphy?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Engraphy safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Engraphy still maintained?

Yes — the latest release is v0.3.0 (18 Sep 2026), and the last commit was a month ago. The repository has 0 stars.