agentic-memory-engine

satvik-sahore/agentic-memory-engine

★ 0 stars Python AI/LLM Updated today

A production-grade long-term memory microservice & MCP server for AI agents featuring two-phase fact extraction, state conflict reconciliation, and Qdrant vector search.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "agentic-memory-engin": {
      "command": "uvx",
      "args": [
        "agentic-memory-engine"
      ]
    }
  }
}

Or install with pip: pip install agentic-memory-engine

README Excerpt

> A production-grade **Long-Term Memory Microservice & Model Context Protocol (MCP) Server** for AI Agents. Enables continuous, cross-session learning by dynamically extracting atomic user facts, resolving state conflicts (`ADD`, `UPDATE`, `DELETE`, `NOOP`), and persisting vectors in Qdrant. --- Traditional RAG and naive chat-history appending have critical flaws:

agentic-memory-engine

Quick Install

README Excerpt

Related AI/LLM Servers