Brethof AI · October 6, 2026 · updated November 19, 2026: the Brain now runs on your own computer or server
If you run an AI agent, you already know the ritual. You open a session and re-explain the project: what it is, what was decided, what was rejected, why the build works the way it does. Some people keep this in md files — a CLAUDE.md here, a notes file there — and soon the agent is lost in an md jungle, reading stale half-truths from March alongside the things that are true today. Either way, you are the memory. You retype the same context a thousand times a day, and the agent repays you by re-proposing the approach you killed months ago, because nothing told it not to.
The models are getting smarter every month. But a model without memory meets your project fresh every morning. Without memory, they're all dumb — the intelligence is wasted on re-deriving what you already told it.
Before describing ours, here is what a fix has to pass. Three tests.
Already there when the session starts. A brief opens every session — where things stand, what was settled, what comes next — and on every prompt, the records that bear on that prompt arrive with it. No tool calls. No turns spent hunting through files. If the agent has to go looking, the memory isn't memory, it's a library with bad opening hours.
It keeps what the conversation settled. Not every half-thought on the way — what the exchange actually concluded. A memory that archives noise is a junk drawer with a search box.
It remembers decisions, not just facts. Records keep what is true now. But "why is it like this?" needs the history: every decision dated, with its reason and the option it beat. History never rewritten — a reversal is a new line, and the old way stays on record as the old way.
I tried most of the memory systems for AI agents. Each did a part of this, and none did what I needed. So I spent almost a year building the one that does.
brethof-brain is memory for AI agents that is already there when the session starts.
It works in layers, because a memory is more than a transcript. The full chat history — every session kept in full and searchable by keyword or by meaning. Curated records — the current truth of each project, which the memory builds itself by reading your conversations: it keeps what the conversation settled, reconciles new facts against old ones, and you never file anything by hand. Rules — standing instructions, yours, loaded whole at every session start, so every agent on every project works the same way. Playbooks — a procedure written once as markdown, run by any agent on any project the same way every time.
Under the records sits the graph of decisions: every decision dated, with its reason, what it replaced, what was tried and rejected along the way. When your agent suggests the thing you rejected back in March, the line saying so — with the day and the reason — comes back with the search. And the Ledger quietly catches the things you said you'd do, so they're reviewable instead of lost. Check it. You'll find the ideas you thought about and never implemented.
No "save my context" ritual. Nothing to remember. You start a session and say "continue," and you carry on. You can run ten projects at once, each walled off — its own records, rules, graph and Ledger — and nothing bleeds between them. One memory serves many agents: one on the front end, one on the back end, or one building and a second checking its work with the whole record in front of it. Your agent never re-proposes what you already killed, because the memory carries the kill.
We built it because we were the problem. We were fed up explaining the same thing to our agents a thousand times a day. We were lost in the md jungle ourselves. We started in December 2025 with md files, and almost everything from those first three months is gone — that is what md files do. In March we moved it onto a database, and every conversation since April is still there, searchable. Our own days run five to seven projects with several agents in parallel on one shared memory — this product was not tested on a demo tenant, it is proven every working day on its own makers, and it has been running since December 2025.
Two convictions drove the design. Teach your agent, don't gate it — memory should make the agent smarter, not add steps between you and it. And AI should do the work for the human. We try to do the work for you.
Everything. Since November 19, 2026 the Brain runs entirely on your own computer or server: the memory, the search and all the work that turns conversation into memory. We keep nothing of it and run nothing of it. The only thing the software tells us is the licence check: which installation it is and how many devices it has.
The memory is encrypted on disk under a passphrase you hold. The thinking is done by the model you choose: your own, at any OpenAI-compatible address, or ours through providers bound by contract not to log, retain or train on what passes through. Every computer, agent or app that uses the memory is a device you approve, with its own key.
You own the data: it is on your own disk. Export the whole history, delete a project, redact an exact phrase. And the source is public: read what it does on GitHub.
One command on the computer or server that will hold your memory:
curl -fsSL https://downloads.brethof.ai/brain/local3/get.sh | bash
It prints the address of your settings page. Connect it to your account, choose your model, pair each machine with a code you approve, and install your agent's plugin.
Five devices are free per account; each one after that is $5 a month or $50 a year. No limit from us on memories, projects, agents, storage or messages — recall is never metered.
It works with Claude Code, Codex, Qwen Code, OpenCode, Kilo Code, dsh, OpenClaw, Hermes Agent, GitHub Copilot CLI, Pi, CodeBuddy, Devin CLI, Kiro CLI, Qoder CLI, goose, Antigravity CLI, Cline, Amp, MiniMax Code and Grok Build.
That's the whole pitch. Install it, open a session, and the next one starts with your agent already briefed.
Dictation, transcription and translation that run on your own machine. Buy once.
Memory for your AI agents — records, rules, the full history and the graph of decisions, already there when a session starts. It answers before you ask.
Tell us what you need. Our written answer within two working days.
Our YouTube channel. A cyber-tiger host walks through local AI tools and what they actually do.
Short video reviews of software and AI tools: used on camera, with a verdict nobody can buy.
Curated GitHub lists for AI coding agents, MCP servers, local AI and Linux for AI. Every entry carries a source link.