1. Conduid
  2. RAG
  3. Engram Mem
MCP server · RAG

Engram Mem

by · github.com/docaohieu2808/Engram-Mem

Persistent memory for AI agents. Dual-memory system (episodic vector + semantic graph) with CLI, HTTP, MCP & WebSocket interfaces.

Unclaimed last commit 7 months ago aiai-agentsai-memorychromadbclaude-codecursorepisodic-memoryknowledge-graphllmmcpmcp-servermemorypythonragsemantic-memoryvector-database
InstallView source
34Low

Scored a month ago · breakdown

About Engram Mem

Engram Mem is an MCP server published by docaohieu2808 in the RAG category: persistent memory for AI agents. Dual-memory system (episodic vector + semantic graph) with CLI, HTTP, MCP & WebSocket interfaces.

The repository has 2 stars and 1 forks, with the last commit 7 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/docaohieu2808/Engram-Mem

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 (21)

engram_add_entityAdd/update entity node to knowledge graph

Parameters not published.

engram_add_relationAdd/update relationship edge between entities

Parameters not published.

engram_askSmart query — auto-routes to recall or think based on intent

Parameters not published.

engram_auto_feedbackAuto-detect feedback sentiment from text

Parameters not published.

engram_cleanupDelete all expired memories

Parameters not published.

engram_cleanup_dedupDeduplicate similar memories by cosine similarity threshold

Parameters not published.

engram_feedbackRecord positive/negative feedback (adjusts confidence)

Parameters not published.

engram_get_memoryRetrieve full memory content by ID or 8-char prefix

Parameters not published.

engram_ingestDual ingest: extract entities + store memories from chat

Parameters not published.

engram_meeting_ledgerRecord structured meeting (decisions, action items, attendees)

Parameters not published.

Show all 21 tools
engram_query_graphQuery knowledge graph (keyword, type, related-to)

Parameters not published.

engram_recallSearch episodic memories (compact or full) with filtering

Parameters not published.

engram_rememberStore episodic memory with type, priority, tags, expires, topic-key

Parameters not published.

engram_session_contextRetrieve memories from active session

Parameters not published.

engram_session_endEnd active session

Parameters not published.

engram_session_startBegin new conversation session

Parameters not published.

engram_session_summaryGet summary of completed session

Parameters not published.

engram_statusShow memory statistics (episodic count, semantic nodes/edges)

Parameters not published.

engram_summarizeSummarize recent N memories into insights via LLM

Parameters not published.

engram_thinkReason across episodic + semantic memory via LLM

Parameters not published.

engram_timelineGet chronological context around a memory (±window minutes)

Parameters not published.

Ask AI

✦

Ask AI about Engram Mem

Powered by Claude · Grounded in docs

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

Security checks

6 checks have not been run yet.

Questions

About Engram Mem

How do I install Engram Mem?

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

Is Engram Mem 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 Engram Mem still maintained?

The last commit was 7 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.