mnemo-mcp

Overview

Open-source MCP Server for persistent AI memory with embedded sync, featuring hybrid search, knowledge graph, and importance scoring.

Capabilities

• • resource handlers
• • prompt templates
• • authentication support
• • database integration
• • github integration
• • workflow automation support

Best For

mnemo-mcp is an open-source MCP server for persistent AI memory with embedded sync, supporting hybrid search and knowledge graph.

Decision Snapshot

• • GitHub stars: 4
• • Forks: 2
• • Source provenance count: 1
• • Last seen: 4/15/2026
• • Published: 3/20/2026

Installation / Setup

# Pre-download embedding model (~570MB) and validate API keys && uvx mnemo-mcp warmup && # With cloud embedding (validates API key, skips local download if cloud works) && API_KEYS="JINA_AI_API_KEY:jina_..." uvx mnemo...

Usage

API_KEYS

Features

• • **Hybrid search** -- FTS5 full-text + sqlite-vec semantic + reranking for precision
• • **Knowledge graph** -- Automatic entity extraction and relation tracking across memories
• • **Importance scoring** -- LLM-scored 0.0-1.0 per memory for smarter retrieval
• • **Auto-archive** -- Configurable age + importance threshold to keep memory clean
• • **STM-to-LTM consolidation** -- LLM summarization of related memories in a category
• • **Duplicate detection** -- Warns before adding semantically similar memories
• • **Multi-machine sync** -- JSONL-based merge sync via embedded rclone (Google Drive, S3, Dropbox)
• • **Proactive memory** -- Tool descriptions guide AI to save preferences, decisions, facts

Use Cases

• • Supports capabilities such as: resource handlers; prompt templates; authentication support.
• • Common usage themes: ai-memory, antigravity, claude, codex.

Supported Clients / Integrations

• • resource handlers
• • prompt templates
• • authentication support
• • database integration
• • github integration
• • workflow automation support

Compatibility Signals

• • Claude Desktop: mentions (Mentioned in approved metadata/docs evidence.)
• • Cursor: mentions (Mentioned in approved metadata/docs evidence.)
• • GitHub: supports (Detected in parser config/capability hints.)

Prompt Examples

Notes / Requirements

• • Primary language: Python
• • License: MIT
• • Documentation coverage: high
• • Parser coverage score: 0.70
• • Source feeds: PyPI RSS + JSON API
• • Topic cluster: coding

Official Links

• Website
• Repository

Source Information

Related MCP Tools