Memory (Knowledge Graph) (official reference server)
Basic persistent memory using a local knowledge graph of entities, relations and observations, so the assistant can remember information about you across chats.
MCP server by shaneholloman · ★ 888 · updated 4 months ago
MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development
Choose your AI client and copy the config.
Add to claude_desktop_config.json — macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Then restart Claude.
{
"mcpServers": {
"mcp-knowledge-graph": {
"command": "npx",
"args": [
"-y",
"mcp-knowledge-graph",
"--memory-path",
"/Users/yourusername/.aim"
]
}
}
}Or add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
{
"mcpServers": {
"mcp-knowledge-graph": {
"command": "npx",
"args": [
"-y",
"mcp-knowledge-graph",
"--memory-path",
"/Users/yourusername/.aim"
]
}
}
}Or add to .vscode/mcp.json in your workspace.
{
"servers": {
"mcp-knowledge-graph": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-knowledge-graph",
"--memory-path",
"/Users/yourusername/.aim"
]
}
}
}Run in your terminal:
claude mcp add mcp-knowledge-graph -- npx -y mcp-knowledge-graph --memory-path /Users/yourusername/.aimRun the server directly:
npx -y mcp-knowledge-graph --memory-path /Users/yourusername/.aimBasic persistent memory using a local knowledge graph of entities, relations and observations, so the assistant can remember information about you across chats.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.