Why How it works Projects & rules Playbooks Install Pricing Affiliates Docs Account Get started free More from Brethof AI Voice Pro brethof-brain 3D Prints Nova Reviews Awesome lists Guides

We only process your memory. We never store it · processing in a secure compute instance in Zurich · the thinking under zero data retention

A memory for AI agents — your agent just remembers

Name: brethof-brain
Author: Brethof AI

You say "continue" and it picks up where you left off — the stack, the decisions, what's next, already loaded. And installing it is one sentence: tell your agent install brethof-brain and it's done — it fetches the client, wires the hooks and checks its own work. Every other developer tool hands you a wall of commands to type. This one you ask for.

Get started free How it works

Free tier · no credit card · recall is never metered or capped

Say “continue” and carry on It answers before you ask Installed by asking your agent Your memory, encrypted under your passphrase

brethof-brain: stop prompting, start conversations with your agent. It answers before you ask: it searches by itself with every prompt, keeps three memories in one, and lives on your machine or hosted under a key only you hold.

We only process it. We never store it

🇨🇭 Secure compute instance in Zurich — stores none of your memory

Thinking under zero data retention

Full chat history, searchable, protected

Records · rules · graph · notes · playbooks · Ledger

Twenty proven platforms

Why it is different

We only process your memory. We never store it.

There's a reason most "memory" tools end up unused. They're a drawer: you have to remember to open them. You have to recall that the drawer exists, and that the thing you need is in it, and then you have to make the model's next step be "go look in the drawer." That only works when you're diligent enough to ask — which is exactly the moment you won't. Brethof-brain is not a drawer. Four things, and as far as we know no one else offers them together.

We never store your memory

Local, your memory lives on your own machine and nowhere else. Hosted, it is encrypted in Germany under a passphrase only you hold — locked, it is ciphertext to everyone, including us. Our hub reads a piece only when your box sends it one to work on; it keeps it only long enough to understand it, and stores none of it.

🇨🇭

The processing runs in a secure compute instance in Zurich, Switzerland

Every conversation passes through our hub — that is how memory gets made — but the hub only processes: each exchange stays only long enough to be understood, and the hub keeps none of it. It holds your standing rules and each project's one-line purpose, nothing else. It runs in a Tier III+ datacenter.

The thinking is done under zero data retention

The model provider is bound by contract not to log, retain or train on what passes through. We state that as their commitment.

It is already there — most of the time

Rules arrive with almost every message. The records that bear on a prompt arrive with it. A brief opens every session. And when that is not enough, everything ever said can be searched.

What you get

Seven things, one memory

At the start of every session the agent is handed the standing rules, what each project is, where the last sessions left off, and an index of what is known. On every prompt, the records that bear on it are added before the agent answers. Everything is organised by project, each with its own memory, its own knowledge and its own focus, set by a one-line purpose.

📋

Curated records

The current truth of each project, handed to your agent with every message they bear on. The memory curates itself: it reads what was said and keeps what a future session would need, reconciling new facts against old ones.

📜

Rules

Standing instructions, loaded with most messages. Every agent on every project works the same way.

The full chat history

Every session kept in full and searchable. It is protected: it cannot be deleted piecemeal.

🔗

The graph

The graph is the memory of decisions. Every decision dated, with its reason and the option it beat; what was tried, rejected or dropped along the way. When your agent suggests the thing you killed in March, the line saying so — with the day and the reason — comes back with the search. History is never rewritten: a reversal is a new line.

Notes

Your agent's own handover, written by it, loaded at the start of the next session.

Playbooks

A procedure written once and run by any agent on any project. A project's atlas — the map of the whole system — lives here.

The Ledger

Catches, in the background, the things that were said and meant. You check it later.

🔑

You own the data

Export the whole history, delete a project, delete an exact phrase, or delete the account — from the panel, behind your own identity. If our hub is unreachable, the memory keeps recording and your agent's own search keeps answering. The session brief and per-prompt recall wait for the hub. Nothing is lost.

Two editions

Choose where your memory lives

One choice at signup: memory lives local, on your own machine, or hosted, in our cloud, encrypted, in Germany. Both editions run the same memory and connect to the same hub. Plans and packs can change any time; only this choice is made once.

Local your machine

The memory — the records, the archive, the graph, the search — is stored on your machine and nowhere else. Pieces pass through our hub only to be processed; the hub keeps none of them. Needs Docker or Podman, about 3 GB of disk including the memory model, a passphrase and a key from the panel; no elevated privileges. Storage is your own disk, unlimited by us.

☁️

Hosted our cloud, Germany

The whole memory is encrypted under a key derived from a passphrase only you set and hold. It unlocks when you start a session and locks itself after an idle period you choose. While locked it is ciphertext to everyone, including us. If the passphrase is forgotten, no one can open it — and deleting the account still works without it.

Many agents, one memory

Split the work. Neither of them has to be told twice.

Put one agent on the front end and another on the back end of the same project, each with its own key and, on hosted memory, its own permissions, on whichever of the twenty proven platforms suits the job. They work from one memory, so neither has to be told what the other decided — what one of them teaches reaches the other's next prompt as soon as it is curated.

Or run them in turn. One builds; a second checks it later with the whole record of what was done in front of it — the decisions, the reversals, the reasons — instead of a summary somebody had to write.

Not two agents on the same files at the same time. That is not what this is for.

Privacy and security — the heart of it

A secure compute in Zurich. We store almost nothing.

Brethof AI is a company in Poland, in the EU. The processing runs in a secure compute instance in Zurich, Switzerland. Each exchange — and each piece your box sends for judgement — passes through only long enough to be understood; the hub keeps none of it. The only things it holds are your standing rules and one line per project saying what the project is. The instructions, never the conversations.

The thinking goes to a model provider bound by contract not to log, retain or train on what passes through — their commitment, stated as theirs. On the hosted edition, memory is stored and searched in Germany; the processing pass runs on our secure compute in Switzerland; the model pass is transient. Backups are the encrypted memory itself, in Germany, on a short cycle, deleted when the account is.

1 · your machine

The memory stays with you

Records, the archive, the graph and the search live on your box — or, hosted, in a memory locked under your passphrase.

2 · Zurich

One exchange is processed

It passes through the secure compute instance in Zurich — a Tier III+ datacenter — only long enough to be understood. The hub keeps none of it.

3 · zero data retention

The thinking happens

A model under a zero-data-retention contract reads the exchange and answers. Logging, retention, training on what passes through: none of it, by the provider's own contract.

4 · back to you

Only the record returns

What was worth remembering comes back to your memory. The exchange is gone from the hub and the model; your own archive keeps it.

The archive is protected for you: individual messages cannot be quietly deleted; an exact phrase can be redacted; recent history is protected; a whole project or the account can be removed. Full legal detail is on the privacy, terms and security pages.

Why it works this way

Don't cage the model. Teach it.

Most memory systems work by extraction rules and filters — a model is told what to keep, what to drop, how to file. That's caging it.

This memory is run by a model taught the way you'd teach a new hire: this is what's true, this is what changed, this is what we decided. It grows into the shape of your work instead of being fitted with a shape you have to maintain.

Don’t gate models. Teach them.

How we build everything at Brethof AI.

Why keep everything

Summaries are lossy. Your memory shouldn't be.

Summaries are what you have when you can't afford to keep the original. The summary is good until the detail you didn't think to keep is the detail you needed. This memory keeps the current truth — dense and up to date — and prunes the rest, while every session is archived in full and searchable later. Notes are fast but lossy; the recording is the insurance.

Explore

Everything, in plain language

⚙️

How it works

Curated records, rules, the full chat history, the graph, notes, playbooks and the Ledger — and how they arrive on their own.

Projects & rules

Each project has its own memory, its own knowledge and its own focus, set by a one-line purpose. Rules are standing instructions loaded with most messages.

Install

Install the client the harness's own way — a plugin or a native adapter. It talks only to your own memory. Proven on Claude Code (Linux and Windows), dsh, Codex, Qwen Code, Cline, OpenCode, Kilo, OpenClaw and Hermes Agent.

Pricing

The unit is the message — one exchange, a prompt and its reply. No token counts. Everything the memory does under a message is inside its price. Reaching the allowance stops the learning, never recall. Same price everywhere on Earth, on both editions.

See plans →

The free plan needs no credit card. Anyone who subscribes at a founder price keeps that price for as long as they stay subscribed. Get started free

The Brethof network