federated-memory

pm2550/federated-memory

★ 0 stars Python 🧠 Memory/Knowledge Updated today

Self-hosted MCP server for persistent, cross-workspace AI memory

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

Or install with pip: pip install federated-memory

README Excerpt

A self-hosted MCP (Model Context Protocol) server that gives AI coding assistants persistent, cross-workspace memory. Each machine/tool/project gets its own workspace; all workspaces are readable by any connected AI, but writes are scoped -- creating a **federated** knowledge graph that grows with every session.

Tools (20)

MCP_MEMORY_TOKENMCP_MEMORY_URLMCP_TOKENMEMORY_ROOTMEMORY_SYNC_HOMEPORTSYNC_TOKENdelete_knowledgeget_overviewlist_knowledgelist_sessionslist_workspacesread_knowledgeread_sessionregister_workspacesearch_knowledgesearch_sessionsupload_knowledgeupload_sessionwrite_overview

federated-memory

Quick Install

README Excerpt

Tools (20)

Related Memory/Knowledge Servers