A-MEM Agentic Memory System - MCP Server for IDE Integration (Cursor, VSCode) | Dual-Storage: ChromaDB + NetworkX DiGraph with explicit typed edges | Based on Zettelkasten
概览
An agentic memory system for LLM agents based on the Zettelkasten principle. "A-Mem: Agentic Memory for LLM Agents" by Wujiang Xu, Zujie Liang, Kai Mei, Hang Gao, Juntao Tan, Yongfeng Zhang Rutgers University, Independent Researcher, AIOS Foundation - ✅ : Automatic extraction of keywords, tags, and contextual summary - ✅ : Automatic linking of similar memories - ✅ : Dynamic updating of existing memories - ✅ : Intelligent search with graph traversal - ✅ : Ollama (local) or OpenRouter (cloud) - ✅ : Configuration via .
README
以下为原文 README 节选，完整内容请查看原文。
A-MEM: Agentic Memory System
An agentic memory system for LLM agents based on the Zettelkasten principle.
Based on: “A-Mem: Agentic Memory for LLM Agents”
by Wujiang Xu, Zujie Liang, Kai Mei, Hang Gao, Juntao Tan, Yongfeng Zhang
Rutgers University, Independent Researcher, AIOS Foundation
🚀 Features
Core Features
- ✅ Note Construction: Automatic extraction of keywords, tags, and contextual summary
- ✅ Link Generation: Automatic linking of similar memories
- ✅ Memory Evolution: Dynamic updating of existing memories
- ✅ Semantic Retrieval: Intelligent search with graph traversal
- ✅ Multi-Provider Support: Ollama (local) or OpenRouter (cloud)
- ✅ Environment Variables: Configuration via
.envfile - ✅ Graph Backend Selection: Choose between NetworkX (default), RustworkX (3x-100x faster), or FalkorDB (experimental, not fully tested)
- ✅ Parameter Validation: Automatic validation of all MCP tool parameters
- ✅ Safe Graph Wrapper: Edge case handling and data sanitization for robust operations
Advanced Features (New)
- ✅ Type Classification: Automatic classification of notes into 6 types (rule, procedure, concept, tool, reference, integration)
- ✅ Priority Scoring: On-the-fly priority calculation based on type, age, usage, and edge count for better search rankings
- ✅ Event Logging: Append-only JSONL event log for all critical operations (NOTE_CREATED, RELATION_CREATED, MEMORY_EVOLVED)
- ✅ Memory Enzymes: Autonomous background processes for graph maintenance
- Link Pruner: Removes old/weak edges automatically
- Relation Suggester: Finds new semantic connections between notes
- Dead-End Node Auto-Linker: Automatically creates out-connections for dead-end nodes with intelligent filtering
- Summary Digester: Compresses overcrowded nodes with many children
- ✅ Automatic Scheduler: Runs memory enzymes every hour in the background
- ✅ Metadata Field: Experimental fields support without schema changes
- ✅ Researcher Agent: Deep web research for low-confidence queries (JIT context optimization)
- Automatic triggering when retrieval confidence < threshold
- Manual research via
research_and_storeMCP tool - Hybrid approach: MCP tools (if available) or HTTP-based fallbacks (Google Search API, DuckDuckGo, Jina Reader)
- ✅ Local Jina Reader: Support for local Docker-based Jina Reader instance (fallback to cloud API)
- ✅ Unstructured PDF Extraction: Automatic PDF extraction using Unstructured (library or API)
🔄 Relationship to Original Implementation
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手？先看 mcpskill.org 教程 →配置
{
"mcpServers": {
"a-mem": {
"command": "python",
"args": [
"-m",
"src.a_mem.main"
],
"cwd": "C:\\Users\\tobs\\Downloads\\a-mem_-agentic-memory-system\\a-mem_-agentic-memory-system"
}
}
}