mnemon-dev/mnemon
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with Claude Code, OpenClaw, and any CLI agent.
This project gives AI agents, like those built with Claude Code or OpenClaw, the ability to remember information across different sessions. It takes the text and decisions an agent processes, stores them in a smart, connected way, and then helps the agent retrieve relevant past knowledge when it needs to. It's designed for developers building AI agents who want their creations to have persistent, evolving memory.
Use this if you are building AI agents and need them to retain and recall information over long periods and across multiple interactions, beyond what their immediate context window allows.
Not ideal if you're looking for a general-purpose database or a tool to manage memory for human users directly, as this is specifically for AI agent systems.
Stars
23
Forks
3
Language
Go
License
MIT
Category
Last pushed
Feb 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/mnemon-dev/mnemon"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
MemoriLabs/Memori
SQL Native Memory Layer for LLMs, AI Agents & Multi-Agent Systems
volcengine/OpenViking
OpenViking is an open-source context database designed specifically for AI Agents(such as...
mem0ai/mem0
Universal memory layer for AI Agents
zjunlp/LightMem
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
MemTensor/MemOS
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill...