ChatAndBuild launches Living Brain, shared memory for ChatGPT, Claude and Cursor

1. 2:25 PM
   🚨 AI News | TestingCatalog@testingcatalogX

   ChatAndBuild launches Living Brain, shared memory for ChatGPT, Claude, and Cursor

   AIChatAndBuild has launched Living Brain, a shared memory that AI apps such as ChatGPT, Claude, and Cursor can access and edit. Memories saved in one tool can be recalled in another, so users can switch tools without re-explaining context. Memories and chats are stored as pages that update when something changes, keeping every connected tool on the latest version. The quoted post from @ladyxtel gives benchmark claims of 92.2% on LoCoMo, 464ms median retrieval, and up to 22.6x fewer tokens per question.

   
2. 9:18 AM
   Santiago@svpinoX

   Shared memory service lets Codex and Claude Code reuse one knowledge base

   AISantiago (@svpino) describes a shared memory service that connects multiple agents and AI tools so they can reuse the same knowledge. He gives an example of saving information with Codex and retrieving it through Claude Code. He says the setup keeps a portable knowledge base not tied to any single agent and avoids duplicating knowledge across agents.

3. 9:16 AM
   Rohan Paul@rohanpaul_aiX

   Living Brain offers a shared memory layer for AI models and agents

   AILiving Brain stores a user's accumulated context separately from any model, so ChatGPT, Claude, Cursor, Codex and custom agents can read and write the same memory through MCP or an API. It sends only the few memories relevant to each question, which the company says cuts tokens per question by up to 22.6x and cost per task by up to 95%. The company reports 92.2% on LoCoMo and a 3.7s median end-to-end answer, with 464ms median retrieval.

4. 9:15 AM
   elvis@omarsar0X

   Living Brain offers one shared persistent memory for multiple AI agents

   AILiving 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.

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.