Which integrations are available for this server?

Integrates with local Ollama instances to generate semantic embeddings for memories, enabling AI agents to perform semantic search and retrieval. Uses SQLite for local persistent storage of agent memories, conversation history, and session statistics.

engram-mcp

Q: What can you do with this server?

engram-mcp provides persistent semantic memory for AI agents, storing and retrieving memories across sessions using SQLite and local Ollama embeddings (nomic-embed-text) — no API keys or cloud services required. Store memories * remember: Save session memory entries with automatic embedding and graph extraction * remember_user: Store user-scoped memories (facts, preferences) that persist across all sessions Retrieve memories * recall: Semantic search across session memories (falls back to keyword search); can blend in cross-session user facts via userId * recall_user: Search or retrieve all user-scoped memories from any session context * history: Get recent conversation history for a session in chronological order * graph: Query extracted entity relationships and source memories (requires ENGRAM_GRAPH=1) Manage memories * forget: Delete session memories — all, by ID, or before a date * forget_user: Delete user-scoped memories by ID, date, or all at once * consolidate: Compress old working session memories into dense long-term summaries via LLM, archiving originals (supports dry-run preview) * consolidate_user: Consolidate user-scoped working memories into long-term summaries Monitor memories * stats: Session memory counts broken down by role, tier (working/long_term/archived), and graph data * user_stats: Memory statistics for a specific user across all sessions

by Cartisien

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

@cartisien/engram-mcp

Persistent semantic memory for AI agents — MCP server powered by @cartisien/engram

Give any MCP-compatible AI client (Claude Desktop, Cursor, Windsurf) persistent memory that survives across sessions.

npx -y @cartisien/engram-mcp

What it does

Exposes 5 tools to any MCP client:

Tool	Description
`remember`	Store a memory with automatic embedding
`recall`	Semantic search across stored memories
`history`	Recent conversation history
`forget`	Delete one memory, a session, or entries before a date
`stats`	Memory statistics for a session

Memories are stored in SQLite. Semantic search uses local Ollama embeddings (nomic-embed-text) — no API key, no cloud. Falls back to keyword search if Ollama isn't available.

Related MCP server: Mnemo Cortex

Quick Start

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": ["-y", "@cartisien/engram-mcp"],
      "env": {
        "ENGRAM_DB": "~/.engram/memory.db"
      }
    }
  }
}

Restart Claude Desktop. You'll see remember, recall, history, forget, and stats available as tools.

Cursor / Windsurf

Add to your MCP config:

{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": ["-y", "@cartisien/engram-mcp"]
    }
  }
}

Configuration

Env Var	Default	Description
`ENGRAM_DB`	`~/.engram/memory.db`	SQLite database path
`ENGRAM_EMBEDDING_URL`	`http://localhost:11434`	Ollama base URL for embeddings

Local Embeddings (Recommended)

Install Ollama and pull the embedding model:

ollama pull nomic-embed-text

Semantic search activates automatically. Without Ollama, keyword search is used.

Example Usage

Once connected, your agent can:

remember(sessionId="myagent", content="User prefers TypeScript over JavaScript", role="user")

recall(sessionId="myagent", query="what are the user's coding preferences?", limit=5)
# Returns: [{ content: "User prefers TypeScript...", similarity: 0.82 }, ...]

history(sessionId="myagent", limit=10)

stats(sessionId="myagent")
# { total: 42, byRole: { user: 20, assistant: 22 }, withEmbeddings: 42 }

Part of the Cartisien Memory Suite

@cartisien/engram — core memory SDK
@cartisien/engram-mcp — this package, MCP server
@cartisien/extensa — vector infrastructure (coming soon)
@cartisien/cogito — agent identity & lifecycle (coming soon)

MIT © Cartisien Interactive

Available Tools

17 tools

consolidateB

Consolidate old working memories into dense long-term summaries via LLM. Archives originals.

Inputs: sessionId (required), batch, keep, dryRun.

consolidate_userB

Consolidate user-scoped working memories into long-term summaries.

Inputs: userId (required), batch, keep, dryRun.

daily_summaryA

Returns a summary of memories for a given date (YYYY-MM-DD), or today if omitted.

Inputs: sessionId (required), date.

export_memoriesB

Export all session memories as markdown or JSON.

Inputs: sessionId (required), format.

forgetA

Delete session memories. Delete all, one by ID, or entries before a date.

Inputs: sessionId (required), id, before.

forget_userB

Delete user-scoped memories.

Inputs: userId (required), id, before.

graphA

Query the knowledge graph for an entity — returns relationships and source memories. Requires ENGRAM_GRAPH=1.

Inputs: sessionId (required), entity (required).

historyA

Get recent conversation history for a session in chronological order.

Inputs: sessionId (required), limit.

recallA

Retrieve relevant memories via semantic search (falls back to keyword). Searches working + long_term tiers. Pass userId to blend in cross-session user facts.

Inputs: sessionId (required), query (required), limit, userId, +1 more.

recall_by_timeA

Query memories using natural language time expressions like "yesterday", "last week", "this morning", "before 3pm".

Inputs: sessionId (required), expression (required), limit.

recall_recentA

Get the N most recent memories for a session — no query needed.

Inputs: sessionId (required), limit.

recall_userB

Recall user-scoped memories — works from any session context.

Inputs: userId (required), query, limit.

rememberB

Store a memory entry for a session. Embeddings and graph extraction happen automatically.

Inputs: sessionId (required), content (required), role, metadata.

remember_userA

Store a user-scoped memory that persists across all sessions. Use for preferences, identity, long-term facts.

Inputs: userId (required), content (required), role, metadata.

statsB

Memory statistics for a session — total, by role, by tier (working/long_term/archived), graph counts.

Inputs: sessionId (required).

temporal_statsB

Returns temporal statistics about when memories were created — frequency over time, most active periods.

Inputs: sessionId (required).

user_statsB

Memory statistics for a user — total, by role, by tier.

Inputs: userId (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored 2026-05-03 19:35 across 17 tools

Disambiguation5/5

Each tool has a clear, distinct purpose. Tools are separated by scope (session vs. user), operation (remember, recall, forget, consolidate, stats, export, graph, history), and retrieval method (semantic, time-based, recent). No overlapping functionality.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern (e.g., recall_user, forget, stats). Variations like recall_by_time, recall_recent use predictable suffixes. No mixing of naming conventions.

Tool Count5/5

17 tools is appropriate for a memory management system. The number covers all necessary operations (CRUD, search, statistics, export, graph, user-scoped variants) without being excessive.

Completeness4/5

The tool set covers core memory operations: store, retrieve (multiple methods), delete, consolidate, export, and statistics. An explicit update tool is missing, but consolidation serves as an update mechanism. Minor gap, but overall comprehensive.

Maintenance

ActivityNo data

ResponsivenessSyncing

Resources

Related MCP Connectors

agentbay-mcpA
io.github.thomasjumper
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Knowledge & Memory Autonomous Agents Agent Orchestration
21
https://www.aiagentsbay.com/api/mcp
Ace MemoryB
io.github.rudedoggg
Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.
Knowledge & Memory RAG Systems Autonomous Agents
4
https://ais.agentsandswarms.ai/mcp
goldhold
io.github.jerrysrodz
Persistent memory for AI agents. Search, store, and recall across sessions.
Knowledge & Memory Autonomous Agents RAG Systems
2
https://relay.goldhold.ai/mcp
mcp-server
in.creo-memories
Memory system for AI agents with semantic search. Store and recall memories with ease.
Knowledge & Memory Search RAG Systems
2
https://mcp.creo-memories.in

Related MCP Servers

Mnemo - Persistent AI Memory
Knowledge & Memory Workplace & Productivity
n24q02m
A
license
A
quality
A
maintenance
Persistent AI memory with SQLite hybrid search (FTS5 + semantic), built-in Qwen3 embedding, and rclone sync across machines.
Updated 2 days ago (2026-11-14 05:04 UTC)
15
15 npm
12
Apache 2.0
Mnemo Cortex
Knowledge & Memory RAG Systems
GuyMannDude
A
license
Not graded
quality
B
maintenance
Persistent semantic memory for AI agents — hybrid SQLite + FTS5 with DAG-based summaries, context compaction, and 7 MCP tools. Open source, self-hosted, zero API cost.
Updated 2 days ago (2026-11-14 04:58 UTC)
160
MIT
Rememb
Knowledge & Memory Developer Tools Autonomous Agents
LuizEduPP
A
license
A
quality
B
maintenance
Persistent memory for AI agents with sectioned entries (project/user/context/etc), semantic search, CLI, and per-project scope. Local JSON, zero config, no server required.
Updated 13 days ago (2026-11-02 20:16 UTC)
18
5
MIT
Memory Palace
Knowledge & Memory RAG Systems
jeffpierce
A
license
Not graded
quality
D
maintenance
Persistent semantic memory for AI agents, enabling storage, semantic search, knowledge graph connections, and inter-instance messaging across conversations using local models via Ollama.
Updated 9 months ago (2026-02-15 03:47 UTC)
50
MIT