Private beta · summer 2026

One memory.
Every AI. Six products.

Nerrem Brain is an AI assistant that actually remembers — your work, your people, your decisions — and it puts every AI on your team. Each product below adds one job; they share that memory.

The Suite

Six products. One 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.

What each does

Capability by capability.

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.

core-brain
Foundation · the assistant that remembers

The assistant that remembers — everywhere you work.

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.

  • Multi-LLM by design — Claude, GPT, Gemini, and open models; pick per task or mix mid-conversation, and the lineup keeps growing as new models prove out
  • Memory follows you — laptop, desktop, phone, cloud — same Brain, same context, encrypted in transit and at rest, owned by you
  • Smart routing — the mix — match each task to a model that fits it, across OSS and commercial providers, so you're not paying flagship prices for everything
  • CLI or desktop, or both — work in your terminal, in a native app, or alongside Claude Code / Cursor — same Brain underneath every surface
  • Your daily briefing, built in — every product contributes what needs your attention; core-brain stack-ranks it by leverage and impact and shows you the one briefing, no matter which products you've installed
$brain chat # the command center, in your terminal
note-brain
Capture · a note = a task = a reminder

Never lose a thought.

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.

  • Two-tap capture — the anchor interaction; thought in before it evaporates, especially on mobile
  • Plain markdown, yours forevernt-<id> notes with links and tags; no proprietary format, no lock-in
  • Capture-first, organize-later — notes predate Areas and Projects; AI promotes and synthesizes them when you're ready
  • Feeds the whole suite — a captured note becomes a project goal, a task, a draft — wherever it belongs
$brain note # or two taps on your phone
admin-brain
Arrives after the private beta Attend · your Executive Assistant

Your Executive Assistant.

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.

  • Your inbox, handled — email, calendar, and scheduling triaged in one place, so you're not juggling tabs all morning
  • Filters & prioritizes — surfaces only what truly needs the CEO; the rest gets handled in the background or batched for later
  • Drafts your responses — every reply already has a starting draft you can edit and send in seconds
  • Feeds your briefing — what's urgent in your inbox shows up on core-brain's daily briefing, ranked alongside everything else
  • Respects your focus — knows when to wait; the 2-minute clear-the-top pattern, not constant interruptions

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.
project-brain
Evaluate · your Project Coach

Plans that hold the vision. For you and your LLM.

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.

  • The evidence question — "what's the evidence you did this right?" pushed at every milestone; both you and the LLM have to show your work
  • Score & suggested fixes — run on demand today, scheduleable by an agent tomorrow; produces a simple score and concrete next steps
  • Opinionated, not blank-canvas — knows what a healthy project looks like (users, problems, goals, constraints, decisions, risks, tests) and coaches you toward it
  • Compounding context — every assessment makes future LLM work sharper; agents reference the structured state directly, no tokens burned on markdown
  • Travels with you — project state lives in Brain, follows you across devices and across LLMs; no project ever stranded in one tool
$brain project assess --all # the coach asks "where's the evidence?"
agent-brain
Govern · your Chief of AI Staff

Delegation you can trust.

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.

  • AI Staff, not just agents — agents and workflows you can task, supervise, retire, and rehire
  • Workflow Advisor — advises which workflows to build, helps you design and trial them, and integrates the winners into your work
  • Human-in-the-loop by design — sometimes you have the step, sometimes the staff does; either way you stay in command
  • Picks up from project plans — agents pull tasks directly from project-brain; no rebriefing every time
  • CEO controls always — approvals, spend ceilings, sandboxed execution, full audit trail
$brain agent workflow advisor # which workflows to build next
team-brain
Coordinate · the team layer that doesn't own your Brain

A brain your whole team shares.

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.

  • Your Personal Brain stays sovereign — the team layer is additive, never a lock-in; leave with your data and history intact
  • Ratified decisions agents trust — unilateral · democratic · input+decider, signed and durable as team policy
  • Comments-on-anything — durable, signed, threaded, with permalinks that survive years
  • One inbox across every team — mentions, posts, and decisions awaiting you, prioritized across all the teams you're in
  • Federated, not centralisedNerrem Cloud is the default always-on peer; run it on your own hardware instead, or — when your team is mutually reachable — with no central peer at all. Self-hosted and air-gapped deployments work.
$brain team inbox # every team's signal, one prioritized place
Surfaces & interop

Your AI memory travels with you.

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.

Workstation · terminal-native

brain-chat

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.

  • Type-during-stream UX — the input stays live, queued or interrupting
  • Curated tool catalog — explicit opt-in for anything beyond safe defaults
  • Works alongside Claude Code, Codex, Cursor CLI, Goose, & co. (shared MCP)
Workstation · native desktop

brain-desktop

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.

  • Pane-aware chat — the chat knows what's open in the viewer
  • Rich viewer — documents, briefings, agent graphs, project boards
  • Same web bundle serves brain.nerrem.com when you're on a borrowed machine
Workstation · native mobile · Android beta

brain-mobile

Your 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.

  • Capture-first — drop a note in two taps: text, photos, tags, links
  • Native extras — offline capture, share target, camera, microphone dictation
  • Android, in beta — direct download for testers now; app stores to follow
Interop · MCP standard

MCP Server

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.

  • Read-write — context pulled in, conversations captured back
  • Scope-respecting — every MCP call goes through agent-brain's policy edge
  • Tool surface — your installed products' tools become available to any MCP client
The part nobody else has

It's never just one AI.

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.

STRONG

Strong AI when you need it.

Hard problems get the best mind available — no retooling, no starting over when a better model shows up.

CHEAP

Cheap AI when it works.

Routine jobs cost pennies and still get aced. Agents run on budgets they can't exceed, so overnight work never surprises you.

FAILOVER

Failover when it matters.

Caps, outages — the next AI picks up mid-sentence, fully briefed from your memory. The work never notices.

YOUR CALL

Your money, your call.

You decide how your spend splits across strong, cheap, and local — every AI graded across 11 kinds of work on one scale.

The memory is yours. Knowing which AI to trust with what — that's what your brain is for.

Principles

The brain you own.
Four guarantees, built in.

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.

01 · LOCAL-FIRST

You choose where to run Brain.

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.

02 · PROTECTED

Your thinking gets extra protection.

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.

03 · YOURS

Yours to take anywhere.

Your data works for you and only you — we don't train on it, sell it, or analyze 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.

04 · GROWS WITH YOU

Brain grows with your idea.

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.

Coming next

On the horizon.

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.

Planned · being envisioned
data-brain
Query your data — ask anything, upload nothing

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.

One Brain. Many powerups.

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.