{"id":40639979,"url":"https://github.com/verygoodplugins/mcp-automem","last_synced_at":"2026-01-21T08:02:46.629Z","repository":{"id":317455764,"uuid":"1061903989","full_name":"verygoodplugins/mcp-automem","owner":"verygoodplugins","description":"AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:","archived":false,"fork":false,"pushed_at":"2026-01-04T17:58:33.000Z","size":9419,"stargazers_count":17,"open_issues_count":5,"forks_count":5,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-05T00:14:49.784Z","etag":null,"topics":["ai","falkordb","graph-database","memory","nodejs","qdrant","rag","redis","vector-database"],"latest_commit_sha":null,"homepage":"https://automem.ai/","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/verygoodplugins.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-22T14:39:30.000Z","updated_at":"2025-12-31T18:34:03.000Z","dependencies_parsed_at":"2025-10-22T01:13:43.737Z","dependency_job_id":null,"html_url":"https://github.com/verygoodplugins/mcp-automem","commit_stats":null,"previous_names":["verygoodplugins/mcp-automem"],"tags_count":13,"template":false,"template_full_name":null,"purl":"pkg:github/verygoodplugins/mcp-automem","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/verygoodplugins%2Fmcp-automem","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/verygoodplugins%2Fmcp-automem/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/verygoodplugins%2Fmcp-automem/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/verygoodplugins%2Fmcp-automem/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/verygoodplugins","download_url":"https://codeload.github.com/verygoodplugins/mcp-automem/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/verygoodplugins%2Fmcp-automem/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28629922,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-21T04:47:28.174Z","status":"ssl_error","status_checked_at":"2026-01-21T04:47:22.943Z","response_time":86,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","falkordb","graph-database","memory","nodejs","qdrant","rag","redis","vector-database"],"created_at":"2026-01-21T08:02:42.545Z","updated_at":"2026-01-21T08:02:46.622Z","avatar_url":"https://github.com/verygoodplugins.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AutoMem MCP: Give Your AI Perfect Memory 🧠\n\n[![Version](https://img.shields.io/npm/v/@verygoodplugins/mcp-automem)](https://www.npmjs.com/package/@verygoodplugins/mcp-automem)\n[![License](https://img.shields.io/npm/l/@verygoodplugins/mcp-automem)](LICENSE)\n\n**One command. Infinite memory. Perfect recall across all your AI tools.**\n\n```bash\nnpx @verygoodplugins/mcp-automem setup\n```\n\nYour AI assistant now remembers everything. Forever. Across every conversation.\n\nWorks with **Claude Desktop**, **Cursor IDE**, **Claude Code**, **ChatGPT**, **ElevenLabs**, **OpenAI Codex** - any MCP-compatible AI platform.\n\n## The Problem We Solve\n\nEvery AI conversation starts from zero. Claude forgets your coding style. Cursor can't learn your patterns. Your assistant doesn't remember yesterday's decisions.\n\n**Until now.**\n\nAutoMem MCP connects your AI to persistent memory powered by **[AutoMem](https://github.com/verygoodplugins/automem)** - a graph-vector memory service.\n\n## What You Get\n\n### 🧠 Persistent Memory Across Sessions\n\n- AI remembers decisions, patterns, and context **forever**\n- Works across **all MCP platforms** - Claude Desktop, Cursor, Claude Code\n- **Cross-device sync** - same memory on Mac, Windows, Linux\n\n### 🏆 Graph-Vector Architecture\n\n- **11 relationship types** between memories (not just similarity)\n- **Research-validated** approach (HippoRAG 2: 7% better associative memory)\n- **Sub-second retrieval** even with millions of memories\n\n### 🚀 Works Everywhere You Code\n\n| Platform           | Support | Setup Time |\n| ------------------ | ------- | ---------- |\n| **Claude Desktop** | ✅ Full | 30 seconds |\n| **Cursor IDE**     | ✅ Full | 30 seconds |\n| **Claude Code**    | ✅ Full | 30 seconds |\n| **OpenAI Codex**   | ✅ Full | 30 seconds |\n| **Any MCP client** | ✅ Full | 30 seconds |\n\n## See It In Action\n\n### Claude Desktop with Custom Instructions\n\n![Claude Desktop Using Memory](screenshots/claude-desktop-with-instructions.jpg)\n_Claude automatically recalls memories at conversation start using custom instructions_\n\n### Cursor IDE with Memory Rules\n\n![Cursor with Memory](screenshots/cursor-2.jpg)\n_Cursor uses automem.mdc rule to automatically recall and store memories_\n\n### Claude Code with Session Memory\n\n![Claude Code Memory Capture](screenshots/claude-code-1.jpg)\n_Git commits, builds, and deployments automatically stored to memory_\n\n### OpenAI Codex with Memory Rules\n\nOpenAI Codex uses config.toml to automatically recall and store memories\n\n### Your AI Learns Your Code Style\n\n```javascript\n// After 1 week, your AI writes EXACTLY like you\n// ✅ It knows you prefer early returns\n// ✅ It uses your specific variable naming\n// ✅ It matches your comment style\n// ✅ It follows YOUR patterns, not generic best practices\n```\n\n### Decisions That Feel Like Yours\n\n```\nUser: \"Should we use Redis for this?\"\n\nWithout AutoMem:\n\"Consider RabbitMQ, Kafka, or AWS SQS based on your needs...\"\n\nWith AutoMem:\n\"Based on your pattern of preferring boring technology that works,\nand your positive experience with Redis in Project X (March 2024),\nyes. You specifically value operational simplicity over feature\nrichness - Redis fits perfectly.\"\n```\n\n## Quick Start\n\n### 1. Set Up AutoMem Service\n\nYou need a running AutoMem service (the memory backend). Choose one:\n\n**Option A: Local Development** (fastest, free)\n\n```bash\ngit clone https://github.com/verygoodplugins/automem.git\ncd automem\nmake dev\n```\n\nService runs at `http://localhost:8001` - perfect for single-machine use.\n\n**Option B: Railway Cloud** (recommended for production)\n\n[![Deploy on Railway](https://railway.com/button.svg)](https://railway.com/deploy/automem-ai-memory-service?referralCode=VuFE6g\u0026utm_medium=integration\u0026utm_source=template\u0026utm_campaign=generic)\n\nOne-click deploy with $5 free credits. Typical cost: ~$0.50-1/month after trial.\n\n👉 **[AutoMem Service Installation Guide](https://github.com/verygoodplugins/automem/blob/main/INSTALLATION.md)** - Complete setup instructions for local, Railway, Docker, and production deployments.\n\n---\n\n### 2. Install MCP Client\n\nConnect your AI tools to the AutoMem service you just started.\n\n```bash\n# Guided setup - creates .env and prints config for your AI platform\nnpx @verygoodplugins/mcp-automem setup\n```\n\n**When prompted:**\n\n- **AutoMem Endpoint:** `http://localhost:8001` (or your Railway URL if deployed)\n- **API Key:** Leave blank for local development (or paste your token for Railway)\n\nThe wizard will:\n\n- ✅ Save your endpoint and API key to `.env`\n- ✅ Generate config snippets for Claude Desktop/Cursor/Code\n- ✅ Validate connection to your AutoMem service\n\n### 3. Platform-Specific Setup\n\n**For Claude Desktop:**\n\n```bash\n# Setup prints config snippet - just paste into claude_desktop_config.json\nnpx @verygoodplugins/mcp-automem setup\n```\n\n**For Cursor IDE:**\n\n[![Install MCP Server](https://cursor.com/deeplink/mcp-install-light.svg)](cursor://anysphere.cursor-deeplink/mcp/install?name=memory\u0026config=eyJlbnYiOnsiQVVUT01FTV9FTkRQT0lOVCI6Imh0dHA6Ly8xMjcuMC4wLjE6ODAwMSIsIkFVVE9NRU1fQVBJX0tFWSI6InlvdXItYXBpLWtleS1pZi1yZXF1aXJlZCJ9LCJjb21tYW5kIjoibnB4IC15IEB2ZXJ5Z29vZHBsdWdpbnMvbWNwLWF1dG9tZW0ifQ%3D%3D)\n\n```bash\n# Or use CLI to install automem.mdc rule file\nnpx @verygoodplugins/mcp-automem cursor\n```\n\n\u003e **Note:** After one-click install, configure your `AUTOMEM_ENDPOINT` in `~/.cursor/mcp.json` or Claude Desktop config\n\n**For Claude Code:**\n\n#### Option A: Plugin (Recommended)\n\n```bash\n# In Claude Code, install the plugin:\n/plugin marketplace add verygoodplugins/mcp-automem\n/plugin install automem@verygoodplugins-mcp-automem\n```\n\nOnly one Claude Code plugin ships in this repo: `plugins/automem` with the marketplace catalog at `.claude-plugin/marketplace.json`.\n\n#### Option B: CLI Setup\n\n```bash\n# Installs SessionStart hook and MCP permissions\nnpx @verygoodplugins/mcp-automem claude-code\n```\n\n**For OpenAI Codex:**\n\n```bash\n# Add to your Codex MCP configuration\nnpx @verygoodplugins/mcp-automem config --format=json\n\n# Optional: add memory-first rules to this repo\nnpx @verygoodplugins/mcp-automem codex\n```\n\n👉 **[Full Installation Guide](INSTALLATION.md)** for detailed MCP client and platform-specific setup\n\n---\n\n## New: Remote MCP via HTTP\n\nYou can now connect AutoMem to platforms that support remote MCP via **Streamable HTTP** (recommended) or **SSE** transport via an optional sidecar service (deployable to Railway or any Docker host).\n\n- ChatGPT (Developer Mode custom connectors)\n- Claude.ai (web) and Claude Mobile (iOS/Android)\n- ElevenLabs Agents Platform\n\nQuick connect URLs (after deploying the sidecar):\n\n- **Streamable HTTP** (recommended): `https://\u003cyour-mcp-domain\u003e/mcp?api_token=\u003cAUTOMEM_API_TOKEN\u003e`\n- **SSE** (legacy): `https://\u003cyour-mcp-domain\u003e/mcp/sse?api_token=\u003cAUTOMEM_API_TOKEN\u003e`\n- ElevenLabs: `https://\u003cyour-mcp-domain\u003e/mcp` with header `Authorization: Bearer \u003cAUTOMEM_API_TOKEN\u003e`\n\nSee the Installation Guide for complete steps and deployment options.\n\n### Remote MCP Platforms in Action\n\n![ChatGPT Developer Mode – Connector Config](screenshots/chatgpt-connector-config.jpg)\n_ChatGPT Developer Mode: Add your MCP endpoint as a custom connector_\n\n![ChatGPT with AutoMem Memories](screenshots/chatgpt-memories.jpg)\n_ChatGPT using AutoMem memories via remote MCP_\n\n![Claude Web Using AutoMem](screenshots/claude-ai-web-memories.jpg)\n_Claude.ai website connected to AutoMem via remote MCP_\n\n![Claude iOS App](screenshots/claude-ios-app.jpeg)\n_Claude Mobile (iOS) connected to AutoMem via remote MCP_\n\n## What Happens Next\n\n| Timeline   | What Your AI Learns            |\n| ---------- | ------------------------------ |\n| **Hour 1** | Starts capturing your patterns |\n| **Day 1**  | Learns your decision factors   |\n| **Day 3**  | Recognizes your coding style   |\n| **Week 1** | Writes in your voice           |\n| **Week 2** | Makes decisions like you would |\n\n## Architecture\n\n```\n┌─────────────────────────────────────────────┐\n│         Your AI Platforms                   │\n│  Claude Desktop │ Cursor │ Claude Code      │\n└──────────────┬──────────────────────────────┘\n               │ MCP Protocol\n               ▼\n┌──────────────────────────────────────────────┐\n│   @verygoodplugins/mcp-automem (this repo)  │\n│   • Translates MCP calls → AutoMem API      │\n│   • Platform integrations \u0026 rules           │\n│   • Handles authentication                   │\n└──────────────┬───────────────────────────────┘\n               │ HTTP API\n               ▼\n┌──────────────────────────────────────────────┐\n│        AutoMem Service (separate repo)       │\n│        github.com/verygoodplugins/automem    │\n│   ┌────────────┐      ┌────────────┐        │\n│   │  FalkorDB  │      │   Qdrant   │        │\n│   │  (Graph)   │      │ (Vectors)  │        │\n│   └────────────┘      └────────────┘        │\n└──────────────────────────────────────────────┘\n```\n\n**This repo (mcp-automem):**\n\n- MCP client that connects AI platforms to AutoMem\n- Platform-specific integrations (Cursor rules, Claude Code hooks, etc.)\n- Setup wizards and configuration tools\n\n**[AutoMem service](https://github.com/verygoodplugins/automem):**\n\n- Backend memory service with graph + vector storage\n- Deployment guides (local, Railway, Docker, production)\n- API server with FalkorDB + Qdrant\n\n## Features\n\n### Core Memory Operations\n\n- **`store_memory`** - Save memories with content, tags, importance, metadata\n- **`recall_memory`** - Hybrid search with graph expansion and context awareness:\n  - **Basic search**: query, multi-query, tags, time filters\n  - **Graph expansion**: entity expansion (multi-hop reasoning), relation following\n  - **Expansion filtering**: `expand_min_importance` and `expand_min_strength` to reduce noise in expanded results\n  - **Context hints**: language, active file, priority types/tags\n- **`associate_memories`** - Create relationships (11 types: RELATES_TO, LEADS_TO, etc.)\n- **`update_memory`** - Modify existing memories\n- **`delete_memory`** - Remove memories\n- **`check_database_health`** - Monitor service status\n\n### Advanced Recall (v0.8.0+)\n\n**Multi-hop Reasoning** - Answer complex questions like \"What is Amanda's sister's career?\"\n\n```javascript\nrecall_memory({\n  query: \"What is Amanda's sister's career?\",\n  expand_entities: true, // Finds \"Amanda's sister is Rachel\" → memories about Rachel\n});\n```\n\n**Context-Aware Coding** - Recall prioritizes language and style preferences\n\n```javascript\nrecall_memory({\n  query: \"error handling patterns\",\n  language: \"typescript\",\n  context_types: [\"Style\", \"Pattern\"],\n});\n```\n\n### Platform Integrations\n\n#### Cursor IDE\n\n- ✅ **Memory-first rule file** (`automem.mdc` in `.cursor/rules/`)\n- ✅ **Automatic memory recall** at conversation start\n- ✅ **Auto-detects project context** (package.json, git remote)\n- ✅ **Global user rules option** for all projects\n- ✅ **Simple setup** via CLI or one-click install\n\n#### Claude Code\n\n- ✅ **MCP permissions** for memory tools\n- ✅ **Memory rules** in CLAUDE.md guide Claude's memory usage\n- ✅ **Simple setup** - just permissions, Claude decides what to store\n\n#### Claude Desktop\n\n- ✅ Direct MCP integration\n- ✅ Manual and automated workflows\n- ✅ Full memory API access\n\n## Why AutoMem MCP?\n\n### vs. Building Your Own\n\n- ✅ **2 years of R\u0026D** already done\n- ✅ **Research-validated** architecture (HippoRAG 2, MELODI, A-MEM)\n- ✅ **Working integrations** across all MCP platforms\n- ✅ **Active development** and community\n\n### vs. Other Memory Solutions\n\n- ✅ **True graph relationships** (not just vector similarity)\n- ✅ **Universal MCP compatibility** (works with any MCP client)\n- ✅ **7 memory types** (Decision/Pattern/Preference/Style/Habit/Insight/Context)\n- ✅ **Self-hostable** ($5/month vs $150+ for alternatives)\n\n### vs. Native AI Memory\n\n- ✅ **Persistent across sessions** (not just context window)\n- ✅ **Cross-platform** (same memory in Claude, Cursor, Code)\n- ✅ **Structured relationships** (not just RAG)\n- ✅ **Infinite scale** (no context window limits)\n\n## Real-World Results\n\n### Code Review That Knows Your Standards\n\n```\nBefore AutoMem:\n\"Consider adding error handling here.\"\n\nAfter AutoMem:\n\"Missing your standard try/except pattern. Based on your PR#127\nreview comments, you always wrap database calls with specific\nlogging for timeouts. Apply the same pattern here?\"\n```\n\n### Decisions With Context\n\n```\nBefore AutoMem:\n\"Both approaches have tradeoffs...\"\n\nAfter AutoMem:\n\"You chose PostgreSQL over MongoDB for similar use case in Q1 2024.\nYour decision memo cited team expertise and operational simplicity.\nSame factors apply here - go with Postgres.\"\n```\n\n## Documentation\n\n### MCP Client \u0026 Integrations (this repo)\n\n- 📦 **[Installation Guide](INSTALLATION.md)** - MCP client setup for all platforms\n- 🌐 **[Remote MCP via SSE](INSTALLATION.md#remote-mcp-via-sse-sidecar)** - Connect ChatGPT, Claude Web/Mobile, ElevenLabs\n- 🎯 **[Cursor Setup](INSTALLATION.md#cursor-ide)** - IDE integration with rules\n- 🤖 **[Claude Code Setup](templates/CLAUDE_CODE_INTEGRATION.md)** - Memory rules integration\n- 🚀 **[OpenAI Codex Setup](INSTALLATION.md#openai-codex)** - Codex CLI/IDE/Cloud integration\n- 📖 **[MCP Tools Reference](INSTALLATION.md#mcp-tools)** - All memory operations\n\n### AutoMem Service (separate repo)\n\n- 🏗️ **[AutoMem Service](https://github.com/verygoodplugins/automem)** - Backend repository\n- 🚀 **[Service Installation](https://github.com/verygoodplugins/automem/blob/main/INSTALLATION.md)** - Local, Railway, Docker deployment\n- ⚙️ **[API Documentation](https://github.com/verygoodplugins/automem#api-reference)** - REST API reference\n\n## The Science Behind AutoMem\n\nThe AutoMem service implements cutting-edge 2025 research:\n\n- **[HippoRAG 2](https://arxiv.org/abs/2502.14802)** (OSU, June 2025): Graph-vector approach achieves 7% better associative memory\n- **A-MEM** (July 2025): Dynamic memory organization with Zettelkasten principles\n- **MELODI** (DeepMind, 2025): 8x memory compression without quality loss\n- **ReadAgent** (DeepMind, 2024): 20x context extension through gist memories\n\nThis MCP package provides the bridge between your AI and that research-validated memory system.\n\n## Community \u0026 Support\n\n- 📦 **[NPM Package](https://www.npmjs.com/package/@verygoodplugins/mcp-automem)** - This MCP client\n- 🔬 **[AutoMem Service](https://github.com/verygoodplugins/automem)** - Backend repo with deployment guides\n- 🐛 **[GitHub Issues](https://github.com/verygoodplugins/mcp-automem/issues)** - Bug reports and feature requests\n- 🐦 **[@verygoodplugins](https://x.com/verygoodplugins)** - Updates and announcements\n\n## Quick Links\n\n### MCP Client Setup\n\n- [Installation Guide](INSTALLATION.md) - MCP client setup for all platforms\n- [Cursor Integration](INSTALLATION.md#cursor-ide) - IDE rules and configuration\n- [Claude Code Setup](templates/CLAUDE_CODE_INTEGRATION.md) - Memory rules integration\n- [OpenAI Codex](INSTALLATION.md#openai-codex) - Codex integration\n- [Changelog](CHANGELOG.md) - Release history\n\n### AutoMem Service\n\n- [Service Repository](https://github.com/verygoodplugins/automem) - Backend source code\n- [Service Installation](https://github.com/verygoodplugins/automem/blob/main/INSTALLATION.md) - Local, Railway, Docker deployment\n\n## Contributing\n\nWe welcome contributions! Please:\n\n1. Fork the repository\n2. Create a feature branch\n3. Make your changes with tests\n4. Submit a pull request\n\n## License\n\nMIT - Because great memory should be free.\n\n---\n\n**Ready to give your AI perfect memory?**\n\n```bash\nnpx @verygoodplugins/mcp-automem setup\n```\n\n_Built with obsession. Validated by neuroscience. Powered by graph theory. Works with every MCP-enabled AI._\n\n_Designed by Jack Arturo at [Very Good Plugins](https://verygoodplugins.com)_ 🧡\n\n**Transform your AI from a tool into a teammate. Start now.**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fverygoodplugins%2Fmcp-automem","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fverygoodplugins%2Fmcp-automem","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fverygoodplugins%2Fmcp-automem/lists"}