Quick Install

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

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mem-zero": {
      "command": "uvx",
      "args": [
        "mem-zero"
      ]
    }
  }
}

Or install with pip: pip install mem-zero

README Excerpt

<p align="center"> <img src="banner.png" alt="mem-zero" /> </p> Self-hosted memory server for AI coding assistants. Store, search, and manage persistent context across sessions — so your tools remember what happened last week without stuffing everything into the context window. Each project gets its own isolated vector collection. When you store a memory, an LLM extracts atomic facts, deduplicates against existing memories, and embeds them for semantic search. The result is a clean, searchable m

Tools (20)

API_KEYBUNDLED_EMBED_MODELBUNDLED_MODEL_PATHBUNDLED_THREADSCOLLECTION_PREFIXDASHBOARD_PASSDASHBOARD_USERDIAGNOSTICS_ENABLEDEMBEDDER_DIMENSIONSEMBEDDER_MODELEXTRACT_MAX_CHARSHOSTLLM_BACKENDLLM_MODELOLLAMA_BASE_URLOLLAMA_MAX_CONCURRENTOPENAI_API_KEYOPENAI_BASE_URLOPENAI_EMBED_MODELOPENAI_MODEL

mem-zero

Quick Install

README Excerpt

Tools (20)

Related AI/LLM Servers