io.github.verygoodplugins/mcp-automem

Official

by verygoodplugins · TypeScript

MCP AutoMem

Graph-vector memory for AI assistants using FalkorDB and Qdrant

Graph-vector memory system for AI assistants using FalkorDB and Qdrant storage.

Topics

aifalkordbgraph-databasememorynodejsqdrantragredisvector-database

README.md18 KBView on GitHub

AutoMem MCP: Give Your AI Perfect Memory

One command. Infinite memory. Perfect recall across all your AI tools.

bash

npx @verygoodplugins/mcp-automem setup

Your AI assistant now remembers everything. Forever. Across every conversation.

https://github.com/user-attachments/assets/fd79112b-5158-4320-a054-8c18ab1ea314

</div> The guided installer — <code>npx @verygoodplugins/mcp-automem install</code> walks you through local, hosted, or existing-endpoint setup.

Works with Claude Desktop, Cursor IDE, Claude Code, GitHub Copilot (coding agent), ChatGPT, ElevenLabs, OpenAI Codex, Google Antigravity - any MCP-compatible AI platform.

The Problem We Solve

Every AI conversation starts from zero. Claude forgets your coding style. Cursor can't learn your patterns. Your assistant doesn't remember yesterday's decisions.

Until now.

AutoMem MCP connects your AI to persistent memory powered by AutoMem - a graph-vector memory service.

What You Get

🧠 Persistent Memory Across Sessions

AI remembers decisions, patterns, and context forever
Works across all MCP platforms - Claude Desktop, Cursor, Claude Code, OpenAI Codex, Google Antigravity
Cross-device sync - same memory on Mac, Windows, Linux

🏆 Graph-Vector Architecture

11 public authorable relationship types between memories (recall results may also include read-only system/internal relations that are not valid associate_memories inputs)
Research-validated approach (HippoRAG 2: 7% better associative memory)
Sub-second retrieval even with millions of memories

🚀 Works Everywhere You Code

Platform	Support	Setup Time
Claude Desktop	✅ Full	30 seconds
Cursor IDE	✅ Full	30 seconds
Claude Code	✅ Full	30 seconds
GitHub Copilot	✅ Full	2 minutes
OpenAI Codex	✅ Full	30 seconds
Google Antigravity	✅ Full	30 seconds
Any MCP client	✅ Full	30 seconds

See It In Action

Claude Desktop with Personal Preferences

Claude Desktop Using Memory Claude automatically recalls memories using the Personal Preferences template

Cursor IDE with Memory Rules

Cursor with Memory Cursor uses automem.mdc rule to automatically recall and store memories

Claude Code with Session Memory

Claude Code Memory Capture Session-start recall plus LLM-judged storage: Claude decides what's durable and stores it via the memory tools

More platform walkthroughs (Codex, Hermes, Antigravity, remote MCP) live in the Installation Guide.

Quick Start

1. Set Up AutoMem Service

You need a running AutoMem service (the memory backend). Choose one:

Option A: Local Development (fastest, free)

bash

git clone https://github.com/verygoodplugins/automem.git
cd automem
make dev

Service runs at http://localhost:8001 - perfect for single-machine use.

Option B: Railway Cloud (recommended for production)

One-click deploy with $5 free credits. Typical cost: ~$0.50-1/month after trial.

👉 AutoMem Service Installation Guide - Complete setup instructions for local, Railway, Docker, and production deployments.

2. Install MCP Client

Claude Desktop - One-Click Install

Download and double-click to install AutoMem in Claude Desktop:

⬇️ Download AutoMem for Claude Desktop (.mcpb)

After installing:

Claude Desktop will prompt you for your AutoMem Endpoint (http://127.0.0.1:8001 for local)
Optionally enter your API Key (required for Railway, skip for local)
Click Enable

Then add the paste-ready Personal Preferences starter from templates/CLAUDE_DESKTOP_INSTRUCTIONS.md. That's it: Claude now has persistent memory and knows when to use it.

Other Platforms

Connect your AI tools to the AutoMem service you just started.

bash

# Guided install - pick where AutoMem runs, verify it, write .env, and
# configure your agents (Codex, Claude Code, Cursor, OpenClaw, Hermes)
npx @verygoodplugins/mcp-automem install

Every change is shown in a review plan before anything is written, and each modified file keeps a .bak backup. Add --dry-run to preview, --yes to apply non-interactively. See the Installation Guide for all flags.

Just need the .env + config snippets without the agent setup? Use the lighter wizard:

bash

# Creates .env and prints config for your AI platform
npx @verygoodplugins/mcp-automem setup

When prompted:

AutoMem Endpoint: http://localhost:8001 (or your Railway URL if deployed)
API Key: Leave blank for local development (or paste your token for Railway)

The wizard will:

✅ Save your endpoint and API key to .env
✅ Generate config snippets for Claude Desktop/Cursor/Code
✅ Validate connection to your AutoMem service

3. Platform-Specific Setup

For Claude Code (plugin — recommended):

text

# In Claude Code:
/plugin marketplace add verygoodplugins/mcp-automem
/plugin install automem@verygoodplugins-mcp-automem

Claude Code prompts for your AutoMem URL and API key at enable time, bundles the MCP server and silent recall/store-tracking hooks, and auto-updates. Prefer hooks and permissions written directly into ~/.claude/ instead? Run npx @verygoodplugins/mcp-automem claude-code.

On Windows, the hook payload assumes a POSIX shell environment such as Git Bash, MSYS2, or WSL — only bash is required (the hooks are pure bash+sed).

For Cursor IDE:

bash

# Or use CLI to install automem.mdc rule file
npx @verygoodplugins/mcp-automem cursor

Other platforms — Claude Desktop (one-click .mcpb above, plus the Personal Preferences template), OpenAI Codex, Hermes Agent, Google Antigravity, and GitHub Copilot:

👉 Full Installation Guide for every platform's setup and verification steps

Remote MCP via HTTP

An optional sidecar service (deployable to Railway or any Docker host) connects AutoMem to platforms that support remote MCP over Streamable HTTP or SSE — ChatGPT (Developer Mode connectors), Claude.ai web and Claude Mobile, and ElevenLabs Agents.

👉 Remote MCP setup for deployment, connect URLs, and per-platform screenshots.

Architecture

code

┌─────────────────────────────────────────────┐
│         Your AI Platforms                   │
│  Claude Desktop │ Cursor │ Claude Code      │
└──────────────┬──────────────────────────────┘
               │ MCP Protocol
               ▼
┌──────────────────────────────────────────────┐
│   @verygoodplugins/mcp-automem (this repo)  │
│   • Translates MCP calls → AutoMem API      │
│   • Platform integrations & rules           │
│   • Handles authentication                   │
└──────────────┬───────────────────────────────┘
               │ HTTP API
               ▼
┌──────────────────────────────────────────────┐
│        AutoMem Service (separate repo)       │
│        github.com/verygoodplugins/automem    │
│   ┌────────────┐      ┌────────────┐        │
│   │  FalkorDB  │      │   Qdrant   │        │
│   │  (Graph)   │      │ (Vectors)  │        │
│   └────────────┘      └────────────┘        │
└──────────────────────────────────────────────┘

This repo (mcp-automem):

MCP client that connects AI platforms to AutoMem
Platform-specific integrations (Cursor rules, Claude Code hooks, etc.)
Setup wizards and configuration tools

AutoMem service:

Backend memory service with graph + vector storage
Deployment guides (local, Railway, Docker, production)
API server with FalkorDB + Qdrant

Features

Core Memory Operations

store_memory — Save memories with content, tags, importance, metadata. Two modes:
- Single (default): top-level content plus optional fields, including embedding, t_valid, t_invalid, custom id.
- Batch: memories: [...] (≤500 items) for bulk ingestion. Per-item id/embedding/t_valid/t_invalid are not supported in batch mode.
recall_memory — Three modes selected by which params you pass:
- ID fetch: memory_id → fetches one memory by ID; updates last_accessed.
- Tag enumeration: tags + exhaustive: true → paginated exact-match listing for cleanup/audit workflows where ranked recall undercounts. Pair with limit (≤200) and offset; returns has_more.
- Ranked retrieval (default): hybrid search across vector, keyword, tags, recency/state controls, score filters, and graph expansion. Supports state_mode, recency_bias, scope_fallback, expand_respect_tags, min_score, adaptive_floor, and diagnostics such as tag_scope, score_filter, query_time_ms, vector_search, and per-result outside_tag_scope/state_replaces.
associate_memories — Create relationships (11 public authorable types; recall results may also include read-only system relations). Supports single-pair mode and batch mode via associations: [...] (≤500) with relation-specific props like reason, context, resolution, observations, transformation, and role.
update_memory — Modify existing memories
delete_memory — Two modes:
- Single (default): memory_id → removes one memory and its embedding.
- Bulk-by-tag: tags: [...] → bulk-delete all memories matching ANY tag (exact, case-insensitive). No dry-run; verify with recall_memory({ tags, exhaustive: true }) first.
check_database_health — Monitor service health, degraded state, sync counts, vector dimensions, and enrichment diagnostics when the service provides them

Advanced Recall (v0.8.0+)

Multi-hop Reasoning - Answer complex questions like "What is Amanda's sister's career?"

javascript

mcp__memory__recall_memory({
  query: "What is Amanda's sister's career?",
  expand_entities: true, // Finds "Amanda's sister is Rachel" → memories about Rachel
});

Context-Aware Coding - Recall prioritizes language and style preferences

javascript

mcp__memory__recall_memory({
  query: "error handling patterns",
  language: "typescript",
  context_types: ["Style", "Pattern"],
});

Platform Integrations

Cursor IDE

✅ Memory-first rule file (automem.mdc in .cursor/rules/)
✅ Automatic memory recall at conversation start
✅ Auto-detects project context (package.json, git remote)
✅ Global user rules option for all projects
✅ Simple setup via CLI or one-click install

Claude Code

✅ Native plugin - MCP server, silent hooks, and skill in one /plugin install, with enable-time config prompts and auto-updates
✅ LLM-judged storage - session-start guidance nudges Claude to store, verify, and associate durable memories during normal work
✅ Memory rules in CLAUDE.md guide Claude's memory usage

Claude Desktop

✅ Direct MCP integration
✅ Paste-ready Personal Preferences starter template
✅ Full memory API access

Why AutoMem MCP?

vs. Building Your Own

✅ 2 years of R&D already done
✅ Research-validated architecture (HippoRAG 2, MELODI, A-MEM)
✅ Working integrations across all MCP platforms
✅ Active development and community

vs. Other Memory Solutions

✅ True graph relationships (not just vector similarity)
✅ Universal MCP compatibility (works with any MCP client)
✅ 7 memory types (Decision/Pattern/Preference/Style/Habit/Insight/Context)
✅ Self-hostable ($5/month vs $150+ for alternatives)

vs. Native AI Memory

✅ Persistent across sessions (not just context window)
✅ Cross-platform (same memory in Claude, Cursor, Code)
✅ Structured relationships (not just RAG)
✅ Infinite scale (no context window limits)

Documentation

MCP Client & Integrations (this repo)

📦 Installation Guide - MCP client setup for all platforms
🌐 Remote MCP via HTTP - Connect ChatGPT, Claude Web/Mobile, ElevenLabs
🎯 Cursor Setup - IDE integration with rules
🤖 Claude Code Setup - Plugin install, hooks, and memory rules
⚠️ Deprecations - History of the plugin deprecation and its reversal
🚀 OpenAI Codex Setup - Codex CLI/IDE/Cloud integration
🪐 Google Antigravity Setup - Raw MCP config via Antigravity's MCP Store
📖 MCP Tools Reference - All memory operations
📝 Changelog - Release history

AutoMem Service (separate repo)

🏗️ AutoMem Service - Backend repository
🚀 Service Installation - Local, Railway, Docker deployment
⚙️ API Documentation - REST API reference
🧪 Evaluation Lab - Exploratory recall-quality benchmarks and ruleset A/B testing

The Science Behind AutoMem

The AutoMem service implements cutting-edge 2025 research:

HippoRAG 2 (OSU, June 2025): Graph-vector approach achieves 7% better associative memory
A-MEM (July 2025): Dynamic memory organization with Zettelkasten principles
MELODI (DeepMind, 2025): 8x memory compression without quality loss
ReadAgent (DeepMind, 2024): 20x context extension through gist memories

This MCP package provides the bridge between your AI and that research-validated memory system. The backend has also been benchmarked on the neutral Agent Memory Benchmark, including BEAM large-context scaling tiers — reproducible end to end, so you can run it yourself.

Community & Support

💬 Discord - Join the community, get help, share feedback
🐦 X Community - Discussion and updates
📣 @automem_ai - Official announcements
📦 NPM Package - This MCP client
🔬 AutoMem Service - Backend repo with deployment guides
🐛 GitHub Issues - Bug reports and feature requests

Contributing

We welcome contributions! Please:

Fork the repository
Create a feature branch
Make your changes with tests
Submit a pull request with a Conventional Commit title such as fix:, feat:, docs:, or chore:
Do not prefix the PR title with labels like [codex] or [wip] because the squash-merge commit is taken from the PR title

License

MIT - Because great memory should be free.

Ready to give your AI perfect memory?

bash

npx @verygoodplugins/mcp-automem setup

Built with obsession. Validated by neuroscience. Powered by graph theory. Works with every MCP-enabled AI.

Designed by Jack Arturo at Very Good Plugins 🧡

Transform your AI from a tool into a teammate. Start now.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "mcp-automem": {
      "command": "npx",
      "args": [
        "-y",
        "@verygoodplugins/mcp-automem@0.10.0"
      ]
    }
  }
}