nexus-memory

Neboy72/nexus-memory
★ 2 stars Python AI/LLM Updated today
Universal Memory Layer for AI Agents — self-hosted, hybrid search, 3-way: Hermes Plugin · OpenClaw Plugin · MCP Server
View on GitHub → Try with Claude — $10 free →

Quick Install

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

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "nexus-memory": {
      "command": "uvx",
      "args": [
        "nexus-memory"
      ]
    }
  }
}

Or install with pip: pip install nexus-memory

README Excerpt

<p align="center"> <img src="webui/static/assets/logo-transparent.png" width="72" height="72" alt=""/>&nbsp; <img src="docs/images/nexus-banner.svg" alt="Nexus Memory" height="72"/> </p> Your agents forget. Your context gets lost. Your setup knowledge is scattered across chats, tools and repos. **Nexus Memory gives every agent one persistent, self-hosted memory they all share.**

Tools (1)

python3

Topics

aiai-agentsclaude-codecodexcursorembeddingshermesknowledge-graphmcpmemoryopenclawpersistent-memoryqdrantsemantic-searchvector-search