Interlinked.

Features · agent memory · July 2026

How to give Claude Code memory that lasts.

The built-in answer is a file called CLAUDE.md, plain markdown Claude Code reads at the start of every session. Used well, it's the single highest-leverage thing you can do for an agent. But it stops at the edge of one repo, and it's shaped like a path: reorganize your project and the memory quietly goes wrong. Here's how to use it well, and the machine-wide layer that picks up where it stops.

TL;DR · key takeaways

CLAUDE.md is the built-in memory. Plain markdown Claude Code reads at the start of every session. The highest-leverage thing you can set up, and the right home for project rules.

But it stops at one repo. It's keyed to a path, so reorganizing the tree rots the references, and it never reaches the roughly 90% of your disk that was never in git.

A machine-wide vault picks up where it stops. Keyed to each file's OS identity, it spans every repo plus the non-git files, survives any rename or move, and is read and written by every agent you run.

No LLM, and 100% local. It seeds itself from your git history with zero model guesses; a note is searchable in about a millisecond, and at rest the whole engine sits around 44 MB.

Use both. Keep CLAUDE.md for repo rules; add the vault for memory that moves with your files. Everything local is free, forever: the app, whole-machine search, MCP. Hosting starts at $5.99/mo.

Step one · do this first

Start with CLAUDE.md. Most people never use it well.

Memory in Claude Code isn't a hidden setting: it's a file it reads for you. There are three places it can live, and the trick is putting the right thing in each.

PERSONAL

A CLAUDE.md in your home config. Applies to every project you open: your standing preferences, your shell quirks.

PROJECT

A CLAUDE.md checked into the repo root. Shared with your team and loaded at the start of every session in that project.

ON-DEMAND

A CLAUDE.md dropped in a subfolder. Pulled in only when the agent works with files in that part of the tree.

THREE SHORTCUTS WORTH KNOWING
#
append a memory without leaving the session
/memory
open and edit the files directly
@path
import another file so nothing is duplicated
PUT IN

+Build, test and run commands

+Conventions the agent keeps forgetting

+The architecture map: what talks to what

+Gotchas that already cost you a session

KEEP OUT

Anything that changes every day

Secrets and tokens

Transient state ("currently debugging X")

A wall of text: it competes for attention

The other anchor people reach for is ChatGPT-style account memory: it remembers facts about you across conversations. Genuinely useful, but it's conversational and vendor-side: it never saw your codebase, it lives in one company's account, and Claude Code or Cursor can't read it. Two different jobs, and neither one is memory that lives with your files.

The shape of the problem

A memory per repo, versus one under the whole machine.

CLAUDE.md gives every repo its own memory island. Useful inside that repo, blind to every other one, and absent entirely on the roughly 90% of your disk that was never in git. Here is that topology next to a single layer that spans all of it.

PER-REPO CLAUDE.md: one memory island per repowalls between repos: no repo can read anotherweb/CLAUDE.mdknows: this repo · by handapi/CLAUDE.mdknows: this repo · by handdesign-system/CLAUDE.mdknows: this repo · by handeverything else on the machine: documents · configs · downloads · other reposNO MEMORY AT ALL: CLAUDE.md never reaches hereONE LAYER UNDER ALL OF IT ↓MACHINE-WIDE VAULT: one memory, keyed to file identityfolder note ▸ "separate repos that ship together"web/#file-idapi/#file-iddesign-system/#file-iddocs/#file-idconfigs/#file-iddownloads/#file-idone identity per file · survives rename & move · every agent reads + writes · builds itself · 100% localSame files. One memory instead of many islands, and it maintains itself.

The two famous answers, and their edges

Both help. Neither one moves with your files.

 
CLAUDE.md
the built-in file
ChatGPT memory
account-side
Interlinked vault
the machine layer
Lives ina markdown file in the repoone vendor's accounta sealed store on your disk
Keyed toa path in one repoyour loginthe file's OS identity
Sees your actual files?only this repo's tracked filesno: it never saw your machineevery file on the machine
Survives a rename / move?no: references rotn/ayes: the identity never changes
Scopeone repoyour chatswhole machine · every repo + the non-git 90%
Who reads itClaude Codeone vendor's chatevery agent (19 clients)
Upkeepyou, by handthe vendoritself + any agent

None of these are bad tools: keep your CLAUDE.md; it's the right home for project instructions. The gap is structural. Path-keyed and account-keyed memory can't follow the work: reorganize the tree and the references point at folders that no longer exist. Only memory keyed to a file's own identity can move with it, and only a machine-wide index is positioned to do that. More on that failure mode in why agent memory dies on rename.

Where memory should live

A memory that lives with your files, not your repo, not your vendor.

Interlinked keeps a knowledge vault keyed to each file's OS identity, the permanent handle the filesystem assigns the moment a file is created. Notes and relationships hang off that identity, so they span every repo plus the non-git 90% of the disk, survive any rename or move, and are read (and written) by every agent you run. And it doesn't start empty: on a fresh machine it seeds itself from your own history, with zero model guesses: every edge is something you can check.

12 / 12 repos
found and webbed the moment indexing finished on a fresh machine, including the collection of repos that ship together
1.7 s
to replay 8,455 git events and derive 26,958 relationship pairs from the machine's own history
0 LLMs
every note and edge is receipts (counts, hashes, file identities), never a model's hunch

MEASURED ON THE REFERENCE MACHINE: RYZEN 9 9950X3D · 64 GB DDR5 · NVMe · WINDOWS 11 · 4.47M FILES.

Set it up today

Give your agent both kinds of memory.

1

Keep your CLAUDE.md. Project instructions, conventions and commands belong there: it's the right tool for repo-level rules. Nothing here replaces it.

2

Install Interlinked once. One signed installer auto-configures 19 AI clients: Claude Code, Cursor, Copilot, Codex, Windsurf, Zed, Cline and the rest. No JSON editing.

3

Let the vault seed itself. Day one it reads your git history and webs your repos, including the ones that ship together but aren't a monorepo. Nothing to write by hand.

4

Let agents leave notes. A gotcha here, a cross-file tie there: keyed to the file's identity and surfaced to every future agent on the searches it already runs. A save is searchable in about a millisecond; at rest the whole engine sits around 44 MB.

Everything local is free forever, on all your devices, no card. Hosting starts at $5.99/mo. Download for Windows · How the vault differs from RAG and model memory

FAQ · common questions

Questions people ask about giving an agent memory.

Does CLAUDE.md work across more than one repository?

No. Each repo gets its own CLAUDE.md: a memory island, blind to every other repo, and absent entirely on the roughly 90% of your disk that was never in git. That per-repo scope is exactly the gap a machine-wide layer fills.

What happens to my memory when I rename or move a file?

Path-keyed memory breaks: CLAUDE.md references point at folders that no longer exist. Memory keyed to a file's OS identity survives, because that identity is assigned the moment the file is created and never changes on a rename or move.

Do I have to choose between CLAUDE.md and the vault?

No. They do two different jobs. Keep CLAUDE.md for project rules, conventions and commands; add the machine-wide vault for cross-repo memory that moves with your files. Nothing here replaces CLAUDE.md: the vault picks up where it stops.

Does the vault use an LLM, or send my files anywhere?

Neither. No model sits in the loop and nothing leaves the machine: it seeds itself from your own git history with zero model guesses, so every note and edge is something you can check. A save is searchable in about a millisecond, and at rest the whole engine sits around 44 MB.

What does it cost, and how do I set it up?

Everything local is free forever, on all your devices, no card. Hosting starts at $5.99/mo. One signed installer auto-configures your AI clients (Claude Code, Cursor, Copilot, Codex and the rest) with no JSON editing. Download for Windows.

Measured July 2026 · Ryzen 9 9950X3D · 4.47M files · Windows 11← All research