Have you ever wondered how ChatGPT knows what a word means? It does not keep a dictionary. Every word is turned into a long list of numbers, and words that mean similar things end up with similar numbers.
Plot those numbers and meaning becomes geography. Animals gather in one corner, food in another, and a question lands right next to its answer. That is most of what “search by meaning” is.
Or maybe you have wondered how a model decides which earlier words matter. When it reads “the cat sat on the mat”, every word scores every word that came before it, and the scores decide where its attention goes.
The scores are plain multiplication, millions of them at once, which is why this kind of maths runs on graphics cards and not on the processor in your laptop.
Perhaps you have always wanted to know what a “weight” is, the thing models have billions of.
It is one number that says how much an input should count. Move it and the output moves. Training is nothing more than nudging billions of them until the answers come out right.
But before any of that can happen, text has to be cut into pieces a model can count. Words are split into tokens, and every token becomes an id.
That is why models are oddly bad at counting the letters in a word. They never see the letters, only the pieces, the same way you never see the pixels on this page.
If you have ever wondered about any of this, or it has sparked your curiosity, this manual is for you.
It will not teach you to build an AI product. It is not a tutorial and there is nothing to install. It explains, with a lot of pictures, how the machines you talk to every day actually work, and how they remember.
We build long-term memory for AI assistants, so we spend our days inside these systems. This is what we wish someone had drawn for us when we started.
You do not need to be technical. The diagrams do the heavy lifting; you only need to be curious.
Machine Memory
New chapters, by email
The manual is written in the open, a chapter at a time. Leave your address and each new one lands in your inbox the day it is published. Nothing else, and one click to leave.
Want to start now? Read the first chapters
Table of Contents.v0.1
- Memory
- What does it mean for a machine to remember?
- Retrieval.
- Extraction and summaries.
- Forgetting.
- Hardware
- How does a GPU work?
- The memory hierarchy.
- Running a model on your laptop.
- Protocols
- How does MCP work?
- Tool calls.
- Guides
- How Esment works.
- A local MCP memory server.
- Shared memory for Claude Code and Cursor.
- CLAUDE.md or a memory server?
- Persistent memory in Cursor.
- One memory for ChatGPT and Claude.
- Does Claude remember across chats?
- Making ChatGPT remember.
- ChatGPT memory full.
- Long-term memory for agents.
- AI with memory.
- Claude Code context.
Current Progress:
Finished chapters:
16 / 25
Words/chapter:
1.7K
Images/chapter:
2
Current word count:
27.4K
Est word count:
42.8K
Current image count:
36
Common Questions
Common Questions.
Yes. Every chapter is free to read here, with no account and no paywall.
New chapters, by email
The manual is written in the open, a chapter at a time. Leave your address and each new one lands in your inbox the day it is published. Nothing else, and one click to leave.
Want to start now? Read the first chapters