Nerrem Brain is a personal AI assistant built for speed — your projects, notes, decisions and files in one place, with every AI on the market working from them. Each product below adds one job; they all share the same brain.
Each product adds one job to the same brain — capture, attend, coach, delegate, coordinate. They're plug-ins to core-brain, not standalone apps, so they share one memory and compose into more than the sum. Install one, or all of them.
Each product is useful on its own. 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.
Chat on any device; the memory compounds. Every AI on your team, switched automatically — and the mix is yours to set. Core Brain is 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 across CLI, web, desktop, and mobile — on your laptop, your phone, or Nerrem Cloud.
$brain chat # the command center, in your terminal
A note = a task = a reminder — first-class, not a checkbox buried in someone else's app. Jot it and move on; your brain can see every one. Capture in two taps — on your phone between meetings, at a market stall, mid-walk — plain markdown, no folders to pick. Later, Brain links and promotes what matters into projects and tasks.
Capture now. Organize never.
nt-<id> notes with links and tags; no proprietary format, no lock-in$brain note # or two taps on your phone
Admin Brain is your Executive Assistant for everything that comes at you. It reads the avalanche — email, calendar, scheduling, meeting prep — and you get the six that need you, replies pre-drafted. Glance up, clear the top in two minutes, glance back down. Your real work barely notices.
A great assistant handles the inbox so you don't have to.
And because Admin Brain works alongside the rest of the suite, the commitments hiding in your inbox become real work 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 builds the wrong thing, fast: no vision, no requirements, no idea who it's for. Future-you ends up paying for that.
Project Brain is the opinionated coach that fixes that — plans that hold the vision: who it's for, what "good" means, what's next, replanned as reality happens. It asks the one question your LLM never asks itself: "what's the evidence you did this right?" — that you solved a real problem, weighed your options, and tested what mattered.
Project Brain asks. LLMs answer.
$brain project assess --all # the coach asks "where's the evidence?"
Hand off real multi-step work and actually trust it — agents run on budgets they can't exceed, so the stamp money stays stamp money. And most frameworks assume you already know what to automate and how; that's a strange assumption — if you knew, you'd have done it. Agent Brain starts higher up the org chart.
Because the products 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 your projects; Agent Brain spots the repeated work and helps you turn it into a workflow you can actually run.
You say the word. They do the work.
Example: a product with a support inbox. Define the daily workflow once — triage the morning's mail, answer the easy ones, open investigations on the hard ones. After that it runs human-in-the-loop, and the support emails never pile up.
$brain agent workflow advisor # which workflows to build next
A brain your whole team shares — decisions, docs, the why. Nobody waits on Sarah. 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 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 prioritized place
Use Brain as your AI workstation. Or stay in your favorite 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 product 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.
Your memory lives outside the AIs — projects, people, decisions live with you, not inside any one AI's chat history. So every AI on the market can be briefed from the same memory, and Nerrem Brain switches between them automatically. Some cost 1/100th of a commercial AI and ace routine work; some are the exact commercial AIs you already know. We call it the mix.
Hard problems get the best mind available — no retooling, no starting over when a better model shows up.
Routine jobs cost pennies and still get aced. Agents run on budgets they can't exceed, so overnight work never surprises you.
Caps, outages — the next AI picks up mid-sentence, fully briefed from your memory. The work never notices.
You decide how your spend splits — every AI graded across 11 kinds of work on one scale. Everyone starts on Nerrem Cloud; running a model on your own machine is a step you can take later, not a setup you face on day one.
You can’t keep up with which AI is best this week. You don’t have to — knowing which AI to trust with what is what your brain is for.
Brain is architected so these stay true no matter how the suite grows. Every new product, every new surface, every new integration — has to honor these.
Ads cost time and attention you can’t spare. There is no ad business here — no one to sell you to, no reason to study your life, and nothing that would make it worth starting one later. We don’t train on your work, sell it, or analyse your usage.
Move fast without wondering who can read it. Everything runs on your own private volume, encrypted at rest and in transit, with no plaintext mode on our cloud. The layer that matters most — your notes, your conversations, the thinking behind the work — gets a second lock, and you choose who holds the key: leave it with Nerrem for password-reset convenience, or hold it yourself with a passphrase that never touches our infrastructure.
Chat like you’re used to, or drill straight into a project. Add notes, tasks and reminders. Make documents, spin up new work. No assembly required, nothing to configure first — and it gets more useful the more you put in it.
Google Drive, Gmail, your calendar, Slack, Stripe and more connect in a couple of clicks — pulling in what you need, pushing finished work back out. And your own data stays portable: pair another device and it’s simply there, or export everything in standard formats whenever you want.
One more product 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.
Ask anything of your own data; upload nothing. Instead of dumping whole tables into a context window, Data Brain targets the right slice first and reasons over the small result — precise, token-efficient analysis over big datasets. In design.
Install core-brain
first. Add the products you need, when you need them. Every one
composes with the rest — and you never start from zero.