mnemo
Active·★ 12·Apache-2.0·Updated 2026-10-21
Mnemo is an open, free, and unlimited persistent AI memory system featuring hybrid search and embedded synchronization. It integrates full-text search with vector search, temporal decay, and importance boosting for advanced retrieval.
#AI Memory#Hybrid Search#Vector Database#Knowledge Graph#LLM Tools#Context Management#Data Synchronization#CLI Tool
01
Features
01Hybrid retrieval combining full-text search (FTS5) and vector search, fused via Reciprocal Rank Fusion, then re-ranked with temporal decay and importance boost.
02Automatic entity extraction and relation tracking to build a temporal knowledge graph, boosting top search results by graph proximity.
03Multi-machine sync via Google Drive with JSONL-based merge sync, and end-to-end encrypted passport sync using AES-256-GCM and Argon2id for secure cross-device bootstrap.
04LLM-driven compression of older memories and LLM summarization of related memories for STM-to-LTM consolidation, achieving significant token reduction.
05Zero-config local setup using Fastretrieval's built-in Qwen3 ONNX embedding and reranking models, requiring no external API keys for basic operation.
02
Compatibility
Python
Runtime
Verified via docs
SQLite
Database
Verified via docs
Cloudflare
Deployment
Verified via docs
Docker
Container
Verified via docs
Claude Code
Client
Verified via docs
Gemini CLI
Client
Verified via docs
03
Quick start
1
$ /plugin marketplace add n24q02m/claude-plugins
2
$ /plugin install mnemo-mcp@n24q02m-plugins
04
Use cases
↳Providing persistent long-term and short-term memory for AI agents to enhance their context and decision-making.
↳Building and querying a temporal knowledge graph to understand historical states and relationships of entities within an AI system's memory.
↳Synchronizing AI memory across multiple machines or devices securely, enabling a consistent knowledge base for agents.
↳Improving the efficiency of LLM interactions by compressing older memories and consolidating related information.
↳Integrating with various AI clients (e.g., Claude Code, Gemini CLI, Cursor) as an MCP server for advanced memory management.
05
Alternatives
remnic★ 228
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
mcp-local-memory★ 60
A lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.
MAMA★ 15
Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their evolution. SQLite + on-device embeddings, no cloud.
squish-memory★ 12
Local-first memory runtime for AI agents. One command to connect Claude Code, Codex, ChatGPT, MCP workflows, and local agents.
context-harness★ 42
Local-first context ingestion and retrieval for AI tools. SQLite + embeddings + MCP server for Cursor & Claude.
yantrikdb★ 67
Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). AGPL.
Comments
Log in to leave a comment
No comments yet. Be the first!