# Living Brain offers one shared persistent memory for multiple AI agents

> Original title: An effective memory system lets a harness leverage agents' persistent capabilities.

- Source: Elvis Saravia
- Published: 2026-11-04T14:15:08.000Z
- Bad Influence: https://badinfluence.news/items/b3oz7odh5xmeph1wr3dkfuphh
- Original: https://x.com/omarsar0/status/2117983990099452018

## Summary

Living Brain is a persistent memory system that works across ChatGPT, Claude, Cursor, Codex, and custom agents, letting them write to and retrieve from one shared store. The post reports 92.2% on LoCoMo, a 464ms median retrieval time, and up to 22.6x fewer tokens per question.

## Post

An effective memory system lets a harness leverage agents' persistent capabilities.

So decoupling memory from the model is smart. 

Living Brain gives ChatGPT, Claude, Cursor, Codex, and your own agents one shared persistent memory.

They report 92.2% on LoCoMo, with a 464ms median retrieval time. It also uses up to 22.6x fewer tokens per question.

## Quoted post @ladyxtel

> We decoupled memory from the model.
> 
> Living Brain is one persistent brain for ChatGPT, Claude, Cursor, Codex and your own agents. Write in one, retrieve in any.
> 
> 92.2% on LoCoMo. 464ms median retrieval. Up to 22.6x fewer tokens per question.
> 
> LLMs have parameters. Living Brain has plasticity.

https://x.com/ladyxtel/status/2117980022250316282