Back Rohan Paul

Rohan Paul· @rohanpaul_ai · X· 2026-11-04 22:12 · Original publication time AI score47

Living Brain says its shared memory works across ChatGPT, Claude and other toolsMachine translation

AI introduction

Living Brain describes itself as persistent memory shared by ChatGPT, Claude, Cursor, Codex and custom agents: write in one tool and retrieve in another. Its publisher reports 92.2% on LoCoMo and median retrieval of 464 ms; the material does not specify the test conditions.

Original post · AI translation

Rohan Paul@rohanpaul_ai

Translation · refer to the original

@ladyxtel 包括检索在内，端到端只需 3.7 秒，应该能让我的智能体回复显得很迅速。

我也很喜欢这一点：在 ChatGPT 中写入内容，然后在 Claude 中调取，真的能节省很多时间。

ReplyChristel Buchanan@ladyxtel

Translation

我们将记忆与模型解耦了。 Living Brain 是一个持久保存的统一记忆系统，供 ChatGPT、Claude、Cursor、Codex 和你自己的智能体使用。在其中一个工具中写入，就能在任何一个工具中检索。在 LoCoMo 上达到 92.2%。检索延迟中位数为 464 毫秒。每个问题的 token 用量最多减少 22.6 倍。大语言模型有参数。Living Brain 有可塑性。

Original

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.

View this post on X ↗

22:12 · 2026-11-04 · UTC+8

Found an error? Send a correction