AI Agent Memory MCP Server

Name: AI Agent Memory MCP Server
Author: xiangzi1126

@xiangzi1126

Repository Homepage Documentation

About AI Agent Memory MCP Server

Agent-agnostic persistent memory as an MCP Server (SQLite + Chroma + Markdown)

#mcp #memory #agent-memory #persistent-memory #claude-code

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ai-memory": {
      "command": "python",
      "args": [
        "-m",
        "ai_memory",
        "--agent",
        "claude-code",
        "--project-from-cwd"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is AI Agent Memory MCP is an agent-agnostic persistent memory layer exposed as an MCP (Model Context Protocol) server. It gives any MCP client - Claude Code, Qoder, Cursor — a shared, project-local memory store that survives across sessions and agents. Memories live in your project's .ai-memory/ directory and travel with the project; they never leave the machine. Three stores linked by memory id: SQLite (structured source of truth + FTS5 keyword search), Chroma (vector store), and a Markdown mirror (human-readable, editable).

How to use

Install: pip install ai-agent-memory-mcp
On first run a default config is generated at .ai-memory/config.yml. Set an OpenAI-compatible embedding provider (defaults to Volcengine doubao-embedding-vision; SiliconFlow / OpenAI also work) and put the API key in .env.
Register with your MCP client. For Claude Code: claude mcp add ai-memory -s user -- python -m ai_memory --agent claude-code --project-from-cwd
Call who_am_i() to confirm context, then remember() to store and recall() to retrieve. If you switch embedding models later, rebuild vectors with python tests/rebuild_vectors.py.

Key features

Local-first: SQLite + Chroma + Markdown mirror, all in .ai-memory/; no cloud, data stays with the project.
Agent-agnostic: Claude Code / Qoder / Cursor share one store; source_agent stamps each write.
High-hit-rate retrieval: three-way fusion - vector (0.6) + keyword FTS5 trigram (0.25) + title/tag match (0.15).
[[link]] cross-references: memories reference each other by [[title]]; recall and get_memory return a links field.
Any OpenAI-compatible embedding (Volcengine / SiliconFlow / OpenAI / others).
8 MCP tools: remember, recall, get_memory, search_memories, update_memory, forget, list_memories, who_am_i.

Use cases

Give a coding agent durable memory across sessions - past decisions, settled choices, pitfalls hit before.
Cross-agent handoff: Claude Code, Qoder and Cursor on the same project share one store, with source_agent distinguishing writers.
A project knowledge base that's both machine-queryable (vector + keyword) and human-readable (Markdown mirror).
Four categories: user (preferences), project (knowledge), process (work), agent (handoff).

FAQ

Where are memories stored? - In your project's .ai-memory/ (local SQLite + Chroma + Markdown). Only embedding text goes to your configured provider; memories stay local.
Is it tied to Claude Code? - No, any MCP client works; it's agent-agnostic (change --agent for Qoder/Cursor).
Can I switch embedding models? - Yes, any OpenAI-compatible service; edit .ai-memory/config.yml, then rebuild vectors with python tests/rebuild_vectors.py.

Comments

Basic information

More Memory & Knowledge MCP servers

Ultimate Google Docs & Drive MCP Server

a-bonus

The Ultimate Google Docs, Sheets, Drive, Gmail, & Google Calendar MCP Server. This MCP (primarily for use in Claude Desktop) gains full access to your google suite and lets claude do its thing.

605