Does this replace CLAUDE.md?

No. Keep CLAUDE.md for stable per-repo instructions. The brain handles what CLAUDE.md cannot: facts that accumulate as you work, memory across repositories, and knowledge shared with a team under access control.

Is my code sent somewhere for training?

No. You bring your own model key, and nothing you store is used to train any model. The brain stores the durable facts the plugin captures, under your tenant, with a content-blind audit log.

Does it work in every terminal and on multiple machines?

Yes. The key file is what the plugin reads, so once a machine is keyed, every Claude Code session on it syncs. Add the key to another machine and it joins the same brain.

Can I use it solo, without a team?

Yes. The free tier is a personal governed brain. Team features (shared recall, roles, audit) switch on when you invite people.

What is the difference between this and Claude Code's built-in memory?

Built-in memory is per-user notes managed by Claude Code itself. The brain is external, governed infrastructure: shared across agents and people, permission-aware, auditable, and portable to other tools over MCP.

Brain for Claude Code: Governed, Persistent, Shared

AIVM Brain gives Claude Code a persistent, governed second brain. A plugin hooks into Claude Code's lifecycle, captures what matters from each session, and recalls it in the next one, in any terminal, on any machine. Access is permission-aware, every read and write is recorded, and setup is two commands.

Connect Claude Code in about two minutes

The brain ships as a Claude Code plugin. It hooks into the session lifecycle, so capture and recall happen while you work. No curl, no manual API calls.

Create your brain and generate a key. Sign up free at brain.aivm.io, open Connect, pick Claude Code, and generate your agent key. The dashboard gives you a personalized, ready-to-run command.
Install the plugin. Add the AIVM marketplace and install the plugin, then restart Claude Code (plugins load at startup):
```
claude plugin marketplace add AIVMNetwork/aivm-integrations
claude plugin install brain-memory@aivm
```
Prove it remembers. Tell Claude Code a durable fact about your project, end the session so it syncs, reopen, and ask. Answering from a fresh session is the recall proof.

CLAUDE.md is not a memory

Claude Code reads CLAUDE.md at startup, and that file is great for stable instructions: build commands, conventions, the shape of the repo. It is also static, per-repository, and maintained by hand. It does not learn. The decision you made on Tuesday about the migration strategy is not in it unless you stopped and typed it there.

A brain is the moving half of that picture. The plugin watches your sessions and captures the durable facts as they happen: the library you chose and why, the flaky test you diagnosed, the deploy gotcha that cost you an hour. Next session, in that repo or another one, Claude Code recalls it instead of rediscovering it.

Across terminals, projects, and teammates

Session memory tied to one machine solves half the problem. The brain is a service, so the same memory follows you from your laptop to a server to a fresh checkout. Key it once per machine and every Claude Code session syncs to the same place.

It is also shared, on your terms. Your teammate's Claude Code can recall the architecture decision your session captured last sprint, if their role clears it. Each person and each agent gets permission-aware retrieval, so the intern's agent does not read the compensation doc, and there is a tamper-evident record of who recalled what. That is the difference between a shared brain and a shared folder.

What gets captured

Durable facts, not transcripts: decisions and their reasons, project state, preferences, hard-won fixes. You can pin facts, correct them, or shred them from the dashboard, and the governed delete actually deletes.

A governed brain for Claude Code