The memory layer for AI
Give your AIa past.
hippocampOS turns the trail you already leave—email, notes, files, meetings—into private context your AI can actually use.
Scroll to enter
01 / Collect
Your life doesn't fit in a context window.
Connect the sources you already live in. Every useful detail becomes part of a memory that keeps compounding instead of vanishing when the chat ends.
GmailNotionGranolaFiles
02 / Organize
Not a folder. A living graph.
People connect to projects. Decisions connect to meetings. Facts connect back to evidence. Your memory becomes something you can traverse—not another archive you have to search alone.
03 / Understand
Ask once. It already knows the rest.
Invoke a named brain from Claude or ChatGPT. hippocampOS finds the relevant context, carries it into the conversation, and keeps every role of your life in the right scope.
“Invoke my Work brain. What changed since last week?”
04 / Remember
The longer it lives with you, the more useful it becomes.
No more starting from zero. Your AI meets the version of you who remembers.
The whole memory system
Everything your AI is missing.Connected.
Collect context once, organize it into durable memory, and bring the right part into every conversation.
01
Memory beyond the chat
Your context keeps compounding across conversations instead of disappearing when a window closes.
02
AI that learns your world
Bring the right slice of your projects, people, preferences, and history into Claude or ChatGPT when you ask.
03
A graph you can explore
See topics expand into facts and the raw sources behind them. Context stays connected and inspectable.
04
A brain for every role
Keep work, personal life, research, and client context distinct—then see the whole picture in Master Brain.
05
Grounded in your sources
Facts retain their provenance, so you can move from an answer back to the material that supports it.
06
Private by design
Choose what enters each brain, what your AI can retrieve, and what should be removed.
Less rebuilding. Less compute.
Stop paying thecontext tax.
Organize your context once, then retrieve only the useful slice. ChatGPT or Claude spends less time and fewer input tokens rereading the same month of email, notes, and meetings for every question.
Illustrative monthly saving≈13.7Mrepeated input tokens
- Gmail
- 90K20 emails/day × 150 tokens × 30 days
- Notion
- 30K1,000 working tokens/day × 30 days
- Granola
- 40K2,000 note tokens × 20 workdays
(20 questions/week × 52 ÷ 12 − 1 initial build) × 160K tokens≈ 13.7M repeat tokens avoided
Illustrative estimate for five questions on four active days each week. It assumes the full 30-day set would otherwise be rebuilt for every question. Actual savings vary with source volume and how much context the AI product would have processed.
Memory you can see
From source to fact. From fact to understanding.
Open any category, travel into its facts, and inspect the raw sources underneath. The graph makes your AI's context tangible.
Explore your own graphYour memory. Your boundaries.
AI can know you better without knowing everything.
Named brains keep contexts separate. Retrieval brings only the useful slice. Sources and memories stay inspectable and removable.
Private by design Relevant retrieval Source provenance
Plans for durable memory
Choose how muchcontext to keep.
Plans, prices, limits, and availability stay in sync with the current hippocampOS plan catalog.
Memory planAnnual
Spark
$5/month
Billed annually at $60/yr
For one role, done well.
1 brain.
StartCore connectors.
Nightly sync.
Nightly sync.
Works with Claude and ChatGPT.
Most popularAnnual
Synapse
$9/month
Billed annually at $108/yr
Keep work and life separate
2 brains.
StartAll connectors.
On-demand sync.
Email support.
Memory planAnnual
Cortex
$19/month
Billed annually at $228/yr
For the true multi-hat operator
5 brains, plus Master Brain: one view across everything you are.
StartAnnual plans show their monthly equivalent and are billed once per year. Your AI provider remains separate; hippocampOS provides the memory layer.
Stop reintroducing yourself
Your AI is ready for a memory.
Build the context layer that gets more useful every time you use it.
Start building