Tools › LLM Apps & Frameworks › gbrain

gbrain

Organized permanent memory database for AI agents

What it is

gbrain is Garry Tan's organized long-term memory system for AI agents, storing people, companies, and timelines so an assistant can retrieve context. It is aimed at operators who manage many founders, clients, or contacts.

How it works

It uses Postgres as the database with embeddings and BM25 ranking for retrieval, organizing entities and their timelines. It is accessed through an AI assistant or Claude-style interface to give agents structured memory.

Use cases

  • Give an AI assistant structured memory of founders, companies, and meeting timelines.
  • Track client relationships and past interactions for an agency.
  • Build a searchable people-and-company knowledge base for an agent.
  • Maintain a CRM-like memory layer for venture or sales work.

💰 Business opportunities

  • Build a founder or VC relationship-intelligence product using gbrain-style memory.
  • Offer a client-memory setup for agencies and consultancies.
  • Create a sales CRM overlay that gives AI agents structured people and company context.

Featured in 1 video

Cut LLM cost by 95%, replace ElevenLabs, and 10 top GitHub repos

The Next New Thing · 2026-06-05

Similar tools

supermemory

Long-term memory layer that follows your AI across tools

🧠 LLM Apps & Frameworks ★ 31.7k +17 wk TypeScript

MarkItDown

Convert PDFs, Office files, audio and YouTube into clean Markdown

🧠 LLM Apps & Frameworks ★ 196.2k +306 wk Python

OpenViking

Self-evolving context database giving agents organized, searchable memory

🧠 LLM Apps & Frameworks ★ 42.4k +58 wk Python

PixelRAG

Visual web search for agents using screenshots, not just text

🧠 LLM Apps & Frameworks ★ 11k +11 wk Python

claude-mem

Persistent memory that carries agent context between sessions

🤖 AI Agents & Assistants ★ 118k +260 wk TypeScript

Headroom

Compress tool outputs, logs and RAG chunks before the LLM sees them

🛠️ Coding & Developer Tools ★ 79.9k +70 wk Python