Your AI workforce, organised like a real company — Chief of AI Staff to run the operation, Project Coach to discipline your LLM, AI Staff to handle the loops. You're the CEO. Any LLM, every device, the right model for each task.
Each plug-in extends the kernel with a specific job — evaluate, attend, govern, retain, federate. Install one. Or all of them. They compose into something more than the sum of their parts.
Each plug-in is useful alone. Together they form a Brain that knows what you're working on, what's incoming, what's running, what you knew before, and what your team is doing.
Your portable brain — the foundation every other product plugs into, and it goes wherever you do. One memory and every LLM, OSS and commercial, through a single interface — the same across the CLI, web, desktop, and mobile, on your laptop, your phone, or Nerrem Cloud. Use the right model for each task and switch any time, never losing the thread.
$brain chat # the command center, in your terminal
The fastest path from a thought to your Brain. Capture a note in two taps — on your phone between meetings, at a market stall, mid-walk — plain markdown, no folders to pick, no decisions to make. Later, Brain categorizes, links, and promotes what matters into projects and tasks. Capture now, organize never — the structure finds itself.
nt-<id> notes with links and tags; no proprietary format, no lock-in$brain note # or two taps on your phone
Admin Brain is your Executive Assistant for everything that comes at you. Email, calendar, scheduling — the communications layer that would normally eat your morning — triaged, prioritised, and responses pre-drafted, all in one place. Glance up, respond to ten emails, glance back down in two minutes. Your real work barely notices.
A great assistant handles the inbox so you don't have to.
What needs the CEO surfaces on your daily briefing; the rest gets handled in the background or batched for later. And because Admin Brain works alongside the rest of the suite, the commitments hiding in your inbox become real work the rest of your Brain can act on — not another thing to remember.
Connecting Brain to Gmail, Google Calendar, and other providers needs each one's security review — so Admin Brain arrives shortly after the private beta, once those are cleared.
$brain admin focus # 2 minutes. clear the top. back to work.
Your LLM can write any document in the universe — and that's the problem. Without discipline, it'll happily build an entire app with no vision, no requirements, no design spec. Future-you ends up paying for that.
Project Brain is the opinionated coach that fixes that. It asks the one question your LLM never asks itself: "what's the evidence you did this right?" That you're solving a real problem. That you evaluated your options and chose wisely. That you understand your constraints. That you tested what needed testing.
Project Brain asks. LLMs answer.
You run it on demand today — an agent can schedule it tomorrow. It reads every doc you've built, gives your project a simple progress score, and suggests what you and your LLM should fix next. Every future LLM interaction gets sharper because there's a real spec to build on — and agents reference the structured state directly, without burning tokens grinding through markdown.
$brain project assess --all # the coach asks "where's the evidence?"
Most agent frameworks assume you already know what to automate and how to make it work. That's a strange assumption — if you knew, you'd already have done it. Agent Brain starts higher up the org chart.
Because the plug-ins compose, you don't just get agents — you get a real org chart: You (CEO) → Agent Brain (Chief of AI Staff) → Agents & Workflows (AI Staff). Project Brain knows what your projects are. Agent Brain spots the repeated work and helps you turn it into a workflow — a repeatable system for getting it done. Then it runs that workflow human-in-the-loop: sometimes your step, sometimes a staff step, every iteration closer to the project being done.
That's the Workflow Advisor: it advises you on which workflows are worth building, helps you design them, lets you trial them before you commit, and integrates the ones that work into how you operate — so the systems running your day are ones you chose, not ones you cobbled together.
You say the word. They do the work.
Example: an online product with a support inbox. Daily workflow = sort and prioritise the morning's emails, reply to the easy ones, kick off investigations on the hard ones, update docs where needed. Defined once. After that, it runs as a workflow — Agent Brain handles what you've approved for automation, surfaces the rest for a quick decision, and the support emails never pile up.
$brain agent workflow advisor # which workflows to build next
Small teams coordinate without giving up their Personal Brains. Team Brain is a federation of personal Brains, not a shared workspace you all log into — each member stays sovereign and the team layer is purely additive. Shared goals, ratified decisions, and a team-owned knowledge layer live in a team scope the team agrees on, governed by three decision modes: unilateral, democratic, and input+decider.
Decisions that survive the chat scroll.
Comments-on-anything is durable, signed, and threaded — with permalinks that outlive reorgs and member departures. The team's compounding knowledge artifact for years, not the next time someone clears Slack scrollback. And a ratified agreement becomes team policy your agents trust without re-asking.
$brain team inbox # every team's signal, one prioritised place
Use Brain as your AI workstation. Or stay in your favourite LLM tool and pipe Brain through it. Either way, what you learn, decide, and remember follows you — device to cloud to device, federated.
A first-class AI workstation in your terminal. Type while the LLM streams; queue text for the next turn or hit ESC to interrupt. Pipes seamlessly into the rest of your dev flow.
Three-pane native app for Mac, Windows, Linux. Chat on the left, Explorer in the middle, Viewer on the right. The same Brain as the CLI — every plug-in renders here, panes are aware of each other.
brain.nerrem.com when you're on a borrowed machineYour Brain in your pocket — a native Android app wrapping the thumb-first mobile UX in a native shell, with what a browser can't do: offline capture, share-into-app, camera, and mic dictation. Built for capturing on the go.
Brain speaks Anthropic's Model Context Protocol. Point Claude.ai, Claude Code, Cursor, Windsurf, ChatGPT Desktop (any MCP-capable client) at Brain, and your memory and tools are right there — bidirectionally. Queries pull Brain context; conversations save back.
Targeted capture from the LLM tools you already use — Claude, ChatGPT, Perplexity, and the other clients you live in. Your conversations across all of them flow into Brain so you can search across them later — and synthesise across them once data-brain ships.
Each capability emits events. The others subscribe. The result is a Brain where decisions, attention, agents, memory, and team context all reference each other automatically.
Catch a note on your phone between meetings. At your desk, open the CLI and ask your Brain about it — through Claude today, Gemini tomorrow, an OSS model that runs offline on the plane. Same brain every time; you just pick the mind. It's the same brain because the brain is yours — it travels with you, and thinks with whatever mind you choose.
Claude, GPT, Gemini, open-source — point your brain at whichever mind fits the question. It remembers across all of them, so your context carries over.
The same brain answers at every door — capture a thought on one, ask about it from another, and it's already there.
Your laptop, a Mac Mini, a VPS, an air-gapped box — the brain goes where you point it, on hardware you choose.
One continuous brain across everything you do — every project and domain — compounding and getting sharper the more you use it.
You rent the intelligence — and swap it whenever you like. You own the brain it builds, and it travels with you: yours to keep, yours to move, yours to think with any mind you choose.
Brain is architected so these stay true no matter how the suite grows. Every new plug-in, every new surface, every new integration — has to honor these.
Run it on your laptop with the CLI or the desktop app. Run it on Nerrem Cloud. Move it to a VPS, a Mac Mini, an air-gapped box — Brain goes wherever you point it. There are no required servers, so it's always yours to run.
Everything runs on your own private volume, encrypted at rest and in transit. And the layer that matters most — your notes, your conversations, the thinking behind your work — gets a second lock, with you choosing who holds the key: leave it with Nerrem for password-reset convenience, or hold it yourself with a passphrase that never touches our infrastructure, so not even we can read it.
Your data works for you and only you — we don't train on it, sell it, or analyse your usage. And it's always yours to take: pair another device and it's simply there, or export everything in standard formats whenever you want. Yours to keep, for good.
Start solo and Brain amplifies you. Bring on a team — Team Brain is built for startups and small teams — and the same Brain becomes the foundation you build on: shared goals, decisions, and team-owned projects, with no migration and no rebuild. Your Personal Brain is never absorbed. However big your idea gets, you never start over.
One more plug-in is designed and shaped — work to ship is ahead of us. It's slotted into the family so you know what's coming and how it fits.
Precise LLM reasoning over your data — target the right slice first, then reason on the small thing, instead of dumping whole tables into a context window. Token-efficient analysis over big datasets. In design.
Install core-brain
first. Add the plug-ins you need, when you need them. Every one
composes with the rest.