We build AI that remembers.
@chatchat: AI agents you chat with, each carrying a Living Brain. @livingbrain: one memory layer for every AI tool you use.
ChatAndBuild's Living Brain ranks No. 1 on LoCoMo, with our evals reporting 92.2% judged accuracy, compared to a full-context, model-only baseline run of 72.3%.
Living Brain is model-independent memory layer for AI agents. It turns documents, meeting notes and conversations into structured, evolving memory so agents can build on what you already know across AI platforms.
Integrate @livingbrain into your applications and agent systems through its API, MCP, SDK and CLI on https://t.co/DWG35XkNsd.
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.
Build the agent on @chatchat, give it a Living Brain, and it keeps what it learns between runs. Python, TypeScript, API, MCP and CLI all connect.
Learn more 👇
@ladyxtel@X Connect with Python and TypeScript SDKs, the API, or MCP and the CLI. Claude, ChatGPT, Cursor and @chatchat share one brain, and agents read only the relevant memories, so they use fewer input tokens.
Learn more 👇
"What would enough look like for you?"
Our founder Christel Buchanan told @Billionerds she will not stop until the first billion users can have a @livingbrain.
Stay tuned.
She used to lead content for X (Twitter) across Asia.
Now she’s building the memory for AI.
@ladyxtel built @livingbrain: one memory that ChatGPT, Claude and every other AI tool can share.
It hit #2 on Product Hunt, and her company ChatAndBuild earned a place in Google’s startup accelerator.
She runs 20 AI agents herself!
Episode 05 of Billionerds with Christel Buchanan (@ladyxtel).
TOMORROW · November 18 · 4 PM UTC ⏳
Your knowledge is scattered across apps, notes, documents and conversations.
So how does an AI agent know what matters? Mark from our engineering team explains how Living Brain works.
One Living Brain, three agents.
@openclaw gets it in under 5 minutes, and Codex and Claude read from the same brain.
The configs are at https://t.co/dm9YConcmO
We built agent memory the way a compiler builds code.
Overlapping 4,000-character windows. Atomic facts, deduplicated. Candidate pages. A patcher that rewrites pages and keeps what is already known.
10 things about how @livingbrain is built.
A business decision changed on Monday. Nobody retrained the model.
Living Brain keeps memory outside the LLM, so updating what your agents know never touches a weight.
10 design principles behind it, in one video.
Every AI tool you open meets you for the first time.
Our founder Christel Buchanan (@ladyxtel) on why we built Living Brain
Chapters:
00:00 - Introduction & Company Background
01:13 - Living Brain Overview & Developer Tools
02:31 - Memory Compiler & Context Recall
06:03 - Enterprise Benefits & On-Chain Trading Use Cases
07:06 - Core Scoring Formulas & Architecture
09:04 - Long-Term Vision
Set up Living Brain and try it yourself 👇
https://t.co/YtSMg8la1u
In AI you pick two: better, faster or cheaper.
@OpenAI's Thomas Jeng says memory gets you all three.
We wrote up why, with a four-step guide to building your first Living Brain 👇 https://t.co/nY1ehP4X2U
Give your @claudeai a @livingbrain.
1. Go to “Connectors” “Add Connector” then “Add Custom Connector”
2. Name: Living Brain
3. MCP Server URL: https://t.co/qy0Oc2LDhL
4. Default settings will be “Sign in Now” and “Use Claude’s identity”. Click yes.
5. Sign in with your account. That’s it!
Switching to @ChatGPT or Codex from another coding agent used to mean starting over.
With a @livingbrain, your preferences, your ways of working and your past conversations come with you.
OpenAI's Sun Weiran explains 👇
@OpenAI "I gave Codex a Living Brain."
OpenAI's Sun Weiran on carrying your preferences and past conversations into Codex and ChatGPT, so every AI app feels "truly unified and personalized".
Full interview 👇
What a week. We launched @livingbrain.
5.5M views in 72 hours.
Trending X story with 2,311 posts created about us.
#2 on @ProductHunt (even ahead of @OpenAI)
Shipped our official @ChatGPT plugin
Showed how easy it was to go from Claude Code to Codex and more with just @livingbrain.
And we’re just getting started. LFG.
#2 on Product Hunt, and featured in today's Product Hunt newsletter. 🧠
Proud of this team. @livingbrain is one persistent memory across ChatGPT, Claude, Cursor and Codex.
This is the foundation for everything we build next. 👇
Living Brain is #2 on @ProductHunt 🧠
And it just got featured in the Product Hunt newsletter, in front of 350k+ people.
Come say hi 👇 https://t.co/qNvWLlq1gz
OpenAI shipped 20 major announcements in a single day.
Sun Weiran, Applied AI Engineer Lead at @OpenAI, on why agents that keep running need a shared memory.
Chapters:
0:00 Intro
1:21 OpenAI DevDay announcements and releases
3:16 Key industry trends and model advances
9:16 Multi-agent systems and Living Brain
11:00 Developer experience and ecosystem tools
17:51 Conclusion and final takeaways
Set up Living Brain and try it yourself 👇
https://t.co/jsNkL1g4Z5
switching between AI models is easy. bringing all your context with you is the annoying part.
@livingbrain is building a shared memory layer for ChatGPT, Claude, Codex and other agents, so you don't have to keep explaining the same things.
it figures out what's worth remembering and retrieves what matters instead of feeding in your entire history.
their internal tests show up to 22.6x fewer tokens per question, with 464ms median retrieval.
pretty useful if you work across multiple AI tools.