Agent Memory Kit
The basic memory setup for the AI assistant you already work with: a settings block it loads every session, a project file it reads before anything else, and an optional skill that builds the structure and repairs it. It is the foundation, set up by hand. The full, production-ready system is the Memory Engine.
The basic kit, and the full system
This is the basic kit: the memory rules your assistant follows, set up by hand in one project. It is the base everything else sits on, and it is free. The full, production-ready system is the Memory Engine, built on the same idea and run by a machine instead of by habit.
| Agent Memory Kit (free, this page) | Memory Engine | |
|---|---|---|
| What it is | The memory rules, set up by hand | The full, production-ready system |
| Who writes the memory | Your assistant, at four set moments | The engine, every 15 minutes, by itself |
| Which assistants | The one you set it up in | ChatGPT Codex, Claude Code, Claude Cowork, Gemini and Cursor, into one folder |
| Finding something later | Open the file you remember | Search across everything, in English and Arabic |
| Passwords and keys | A rule never to write them down | Hidden before anything is sent, and it stops if it cannot |
| Seeing all of it | Read the files | A dashboard of every person, project and term, rebuilt every 15 minutes |
The kit is where the habit starts. When you want the memory to keep itself, see how the Memory Engine works.
What it is
The memory layer of an AI operating system, and the piece almost nobody installs. Everything else you do with an assistant sits on top of it: without memory, you are re-briefing it every morning for the rest of your life, which is why most people quietly conclude their assistant is dumber than it is.
Right now it opens every session knowing nothing about your work: not what you decided yesterday, not who the client is, not why the last approach was dropped. The notes it does keep end up in a directory that gets wiped between sessions, or in one file while a second file that needed the same edit goes stale.
This kit is the protocol that closes that gap. A small set of rules your assistant reads before it touches anything, and a project file it keeps current while you work.
It comes in three pieces because they load at different moments, and merging them makes all three worse.
1. Global settings
A block you paste once per machine into your tool's global instruction field. It has to run before any file is read, which is exactly why it cannot live inside the project file. Under 2 KB, so it costs almost nothing per session. It defines when your agent reads memory (the map first, then the file whose subject the task actually touches) and when it writes.
2. Project template
A CLAUDE.md or AGENTS.md for the project root, carrying the three sections the global block checks for: a memory map, an active tasks table, and update rules. One per project. This part is the content, not the protocol.
3. Skill
memory-structure, optional. It holds the spec for the instruction file and the logic for repairing one that is missing a section, and it loads only in sessions where the structure is actually being built or fixed, which for most projects is one session in twenty.
Where each piece goes
| Tool | Global settings | Project file |
|---|---|---|
| Claude Cowork | Settings, Cowork instructions | CLAUDE.md |
| Claude Code | ~/.claude/CLAUDE.md | CLAUDE.md |
| Codex | ~/.codex/AGENTS.md | AGENTS.md |
| Cursor | Settings, Rules, User Rules | AGENTS.md |
Piece 1 goes in once per machine, piece 2 once per project. The skill goes to your tool's skills folder when it has one, and gets pasted into the chat on the day you need it when it does not.
The rules your agent ends up following
Installing it
Hand the whole folder to your agent and say "install this kit". It reads 0-INSTALL-ME.md, states which tool it is running in, prints the block you have to paste yourself wherever it cannot write to settings, sets up one project, and finishes with a list of what it wrote and what it skipped. It asks before every write, and it never overwrites an instruction file you already have. About five minutes, most of that reading.
What to check after a week
Open the memory folder and read what is in it. If guesses are sitting there written as facts, the protocol is not doing its job and the file needs pruning. That failure mode is a quiet one, and it is the one worth watching for.
When the basic kit is not enough
The kit gives you the protocol, and the protocol has a ceiling: it remembers what you or your assistant remembered to write down, in the one project you set up. Good sessions still slip through on the days you are moving fast, which are exactly the days worth keeping.
The Memory Engine is the full, production-ready version, and it takes that ceiling off. Every session is captured on its own, with no one deciding what deserves saving. Recall runs by search across everything you have ever worked on, instead of by opening the one file whose name you happened to remember. Your assistant walks into a brand new project already holding the decisions, the people and the constraints from all the others, on day one.
That is the difference between an assistant that keeps notes and one that has a memory.