mcp-ariel-memory

Cipher208/mcp-ariel-memory
★ 0 stars Python AI/LLM Updated 15d ago
Universal Two-Layer Memory MCP Server for AI agents — 37 tools, hybrid search, knowledge graphs, wiki, saga, auth, Docker
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": {
    "mcp-ariel-memory": {
      "command": "uvx",
      "args": [
        "mcp-ariel-memory"
      ]
    }
  }
}

Or install with pip: pip install mcp-ariel-memory

README Excerpt

**Universal Two-Layer Memory MCP Server** A two-layer universal memory system for AI agents. Real MCP Python SDK, async, **37 tools**, stdio + HTTP transports, dashboard, metrics, authentication, automatic backups, external wiki folders, read-only replica. --- mcp-ariel-memory is a production-ready MCP (Model Context Protocol) server that provides persistent, searchable memory for AI agents. It implements a two-layer architecture:

Tools (20)

agent_wikiapi_keysarchived_memoriesaudit_logcore_memoryembedding_cacheepi_edgesepi_nodesepisodesmemory_conflictsmigration_lograg_chunksrag_pagesrag_relationsrate_limitssessionsstaging_memoriestemporal_eventstemporal_linksuser_wiki

Topics

ai-agentknowledge-graphllmmcpmemorypythonrag