Documentation
Everything you need to get started with AutoMem
🚀 Quick Start
Get AutoMem running in under 5 minutes with Railway deployment
⚙️ Installation
Configure AutoMem for Claude Desktop, Cursor, and other MCP clients
✨ Features
Explore memory types, knowledge graphs, and advanced capabilities
📖 GitHub
View source code, contribute, and report issues
Architecture Overview
🗄️ Storage Layer
FalkorDB: Graph database for memory relationships and knowledge graphs
Qdrant: Vector database for semantic similarity search with OpenAI embeddings
🔌 Integration Layer
MCP Server: Model Context Protocol server exposing 6 tools (store, recall, update, delete, associate, health check)
🤖 Client Support
- Claude Desktop (Anthropic)
- Cursor IDE
- GitHub Copilot (via MCP)
- Any future MCP-compatible LLM
☁️ Deployment Options
- Railway: One-click deploy (~$5/month)
- Docker: Self-hosted with docker-compose
- Local: Python development server
Key Concepts
Memory Types
AutoMem categorizes memories into 7 semantic types for better organization and retrieval:
Importance Scoring
Memories are scored 0.0-1.0 based on relevance. Importance automatically decays over time unless reinforced, mimicking human memory.
Knowledge Graphs
Memories can be linked with 11 relationship types:
RELATES_TO, LEADS_TO, EVOLVED_INTO, DERIVED_FROM, EXEMPLIFIES, CONTRADICTS, REINFORCES, INVALIDATED_BY, OCCURRED_BEFORE, PART_OF, PREFERS_OVER
Automatic Consolidation
Background scheduler automatically:
- Decay: Reduces importance of old, unused memories (hourly)
- Creative clustering: Groups related memories (every 6 hours)
- Forgetting: Removes low-importance memories (daily)