@tbpn: Y Combinator's @garrytan says he wants his new project GBrain to be the Postgres for agents: "The thing I realized is, …
Summary
Garry Tan introduces GBrain, a system designed to manage large-scale context for AI agents by loading the most relevant information into their limited context window, likening it to a 'Postgres for agents'.
View Cached Full Text
Cached at: 06/17/26, 05:57 PM
Y Combinator’s @garrytan says he wants his new project GBrain to be the Postgres for agents:
“The thing I realized is, a human can only keep 7, plus or minus 3, things in their head. But a computer with an LLM can keep about three Harry Potter books in its head.”
“Then, when you think about what most computer systems are, you should think of the Library of Alexandria — thousands, maybe millions, of books. It’s even bigger than that. It’s the whole internet.”
“You could basically take all the relevant info about customers, or any person that anyone at the company has ever even met. You can have that in like, 100,000 or a million markdown files that comprises everything that the business is. That’s basically what GBrain can do.”
“The magic moment for GBrain is basically being able to take any ‘book’ that exists in your entire business, and making sure the 3 books that really matter for the thing you’re trying to do are loaded.”
“And that’s basically ASI. You don’t have to write software anymore. You can just straight-up use Hermes agent or OpenClaw plus GBrain.”
Garry Tan (@garrytan): Humans can keep 7 +or- 3 things in their head
Your AI agent can keep 3 whole Harry Potter books in context
You could have 300,000 books in your library
GBrain will make sure your AI agent has the 3 books out of 300,000 loaded in context for your task presently
Big unlock
Similar Articles
@AlperTheKing: Garry Tan's GBrain makes the memory write path the reliability boundary for agent systems, because useful context must …
Garry Tan's GBrain introduces an agent memory system that treats the memory write path as the reliability boundary, using Markdown as source of truth with Postgres and pgvector for retrieval, and exposing operations via CLI and 30+ MCP tools.
@garrytan: What is GBrain? My open source project is a knowledge system, not RAG in a box. It gives agents 8 layers that work toge…
Garry Tan introduces GBrain, an open source knowledge system that improves agent memory with 8 layers, enabling more personalized AI.
@davidNbreslauer: Gbrain by @garrytan is so good, I've now moved by brain onto a dedicated server, that Codex, Claude, OpenClaw, and Herm…
Garry Tan introduces GBrain, an open-source AI agent memory layer that provides synthesis, graph traversal, and gap analysis for coding agents, demonstrating significant improvement over traditional retrieval methods.
@akshay_pachaar: What actually is GBrain? (Y Combinator CEO's personal agent brain) Every agent memory tool you've seen solves a simple …
GBrain is an open-source AI agent memory tool created by YC CEO Garry Tan that uses a self-wiring knowledge graph and markdown-based system of record to enrich and compound agent knowledge autonomously.
@garrytan: GBrain is your company brain
A tweet describes the concept of gBrain as the company brain, an orchestrated system of AI agents organized into department verticals with specialist and sub-agents.