Once upon a time, you had to start every conversation from scratch.
Every chatbot you've ever used suffers from the same affliction: amnesia. You close the tab, and everything is gone. You open a new one, and you're a stranger again. You explain who you are, what you're working on, how you like things done — every single time.
Atlas was born from a simple question: what if your AI assistant actually remembered you? Not just your last message, but the full, rich tapestry of your life — your goals, your preferences, your past decisions, the documents you've been working on, the commitments you've made. What if it could reach into your calendar, read your inbox, and act on your behalf? What if it followed you across every device, always in sync, always ready?
This is the complete story of how Atlas works — told in plain language with warm, simple diagrams. Whether you're curious about the technology, assessing the privacy, or just want a brilliant assistant, you'll understand exactly what makes Atlas different.
The 30-second map
Atlas is a personal AI companion you talk to like a friend. Five layers make it work: you (on any device) chat with the Atlas App, which hands your message to the AI Engine. The engine picks the best brain for the job (AI Provider), reads and writes to your private memory & vault, and reaches into your life through integrations and automations.
How Atlas thinks: one message to one reply
When you send a message, Atlas doesn't fire it raw at an AI. A tier selector first decides how much brainpower your message deserves — a quick "thanks" needs almost nothing; "plan my week from my calendar and inbox" needs your full memory and vault. Atlas then assembles a package: its personality, your relevant memories, and any vault documents that might matter, and hands it to the orchestration engine, which calls the chosen provider and returns the reply.
classifyTier() → memory + vault fetch → orchestration engine call with { messages, tier, context_mode } → provider API → reply. One call from the app; the engine owns provider selection, prompt caching, and automatic failover. The frontend never touches provider keys directly.The right brain for every question
Not every message deserves the same brain. A two-word reply shouldn't cost the same as a 2,000-word life plan. The tier selector routes each message to one of three tiers — each with a different model, a different slice of your history, and a different price. This is what keeps Atlas affordable to run at scale, and fast enough to feel instant on every message.
light; normal conversational turns → standard; long messages, attachments, or planning verbs ("plan", "draft", "analyze", "compare") → deep. The tier becomes a parameter on the orchestration call, selecting both the model and how much of your memory/vault to load.How long chats stay cheap
In a long conversation, your personality prompt and early messages are identical every turn. Without caching, you'd pay full price for them every time. With prompt caching, the provider stores that stable prefix once and reuses it — charging about 10% of normal for the cached portion. For a personal assistant that you chat with all day, this is the single biggest reason it's economically viable to offer unlimited conversations.
cache_control markers on the personality block and the last stable-history message. OpenAI: automatic prefix caching (≥1024 tokens). Google: no explicit caching in v1. The cache lives ~5 minutes; turns within that window are mostly cache reads. This is what makes a 50-message conversation cost the same as a 3-message one.Always on, even on a free tier
Atlas talks to three AI providers — OpenAI, Anthropic, and Google — each on its own account and billing. You might start on Google's free tier, add OpenAI's free credits, and upgrade to Anthropic later. The system handles all of that gracefully, which matters for a consumer product where reliability is everything.
Toggle: an admin can enable or disable any provider at any time. A provider is "available" only if enabled and its key is configured. Failover: if the chosen provider hits a quota or overload error, Atlas silently retries the next available one — so a free tier running dry mid-conversation self-heals instead of breaking. You never see an error. You never lose a thought.
failover: [
{ provider: "OpenAI", status: 429, failover_eligible: true },
]
provider: "Google" // ← who actually served itAtlas remembers you
This is what separates Atlas from every generic chatbot. Atlas doesn't just remember your last message — it holds a structured, long-term model of you, and that model is what makes every reply feel like it's coming from someone who actually knows you.
The five memory types
Atlas stores five kinds of memory, each with a purpose. Facts are stable truths about you — your name, your role, your family. Preferences capture how you like things done — short emails, bullet points over prose, mornings for deep work. Goals are what you're working toward — the promotion, the side project, the trip. Summaries are condensed versions of past conversations so old chats aren't lost. Journal entries are things that happened to you — the meeting that went sideways, the win you landed. Every memory carries an importance score (1–5), searchable tags, and a source date so Atlas can weigh what matters most and what's still current.
How memories are born
You never have to explicitly "save" a memory. As you talk, an auto-summarizer runs in the background every ~10 user messages: it reads the recent thread, extracts anything worth remembering long-term, classifies it into one of the five types, scores its importance, tags it, and writes it to your private memory store. Trivial chatter is skipped; meaningful context is kept. The same pipeline powers briefing absorption — paste in notes or an exported conversation from another tool and Atlas extracts every useful memory from it in one pass.
How memories are retrieved
When you send a message, Atlas doesn't dump your entire memory into the prompt — that would be expensive and noisy. A relevance scorer ranks your memories against your message: title keywords, tag overlap, and content similarity. Only the top few (typically 3 for a standard turn, more for a deep turn) make it into the context window. This is why Atlas can hold thousands of memories and still respond in seconds — it loads the needle, not the haystack.
The three companion stores
Memory is only the beginning. Atlas also maintains three companion stores that turn memory into action. Open items are the things you've committed to — extracted from chat, tagged by life bucket, tracked to completion. Decisions log what you chose, the context, the alternatives, and (later) the outcome — so you can revisit why you picked a path. The vault holds your documents — drafts, plans, articles, spreadsheets — with full version history and sharing controls. Together, memory + open items + decisions + vault give Atlas a complete, living picture of your life.
Cross-device continuity
Every memory, vault doc, open item, decision, and conversation syncs across your devices in real time. Atlas subscribes to live changes on the backend, backfills on window focus, and runs a 60-second safety interval — so the thread you started on your laptop this morning is waiting on your phone this afternoon, complete with its full history. A daily briefing is generated each morning from your open items and overdue tasks, so Atlas greets you with what matters instead of a blank screen.
Your data is yours
A personal assistant that remembers everything about you is also a serious privacy responsibility. Atlas is built privacy-first — not as an afterthought, but as the foundation. Your data is yours: you control it, you can see it, you can delete it, and no one else can touch it.
Layer 1: Access control — your data is locked to you
Every record Atlas holds about you — every memory, every vault document, every conversation, every open item, every decision — is row-level secured. The rule is simple: only the user who created a record can read it. Even though every Atlas user's data lives in the same database, the database enforces that you only ever see your own. There is no "admin can see all user data" path for personal records — your memories are yours alone.
Passcode-locked conversations
Some conversations are more sensitive than others — a personal health matter, a financial decision, a difficult relationship. Atlas lets you passcode-lock any conversation so it's hidden behind a gate screen until you enter the code. The passcode is SHA-256 hashed before it's stored — the plaintext is never saved, not in the database, not in local storage. Even someone holding your unlocked phone can't read a locked conversation without the code. The hash is verified client-side, so the server never sees the plaintext passcode either.
The private vault
Your vault documents — drafts, plans, articles, spreadsheets — are also locked to you. Each document has full version history (every save creates a snapshot you can roll back to) and granular sharing controls: you can grant another Atlas user view, comment, or edit access to a specific document, and you can revoke it at any time. You always know who can see what.
Layer 2: Your rights — see, edit, delete
Privacy isn't just about keeping others out — it's about giving you control. You can see every memory Atlas holds about you. You can edit any memory to correct it. You can delete any memory, conversation, or vault document at any time. And if you delete your Atlas account, all your data is removed — the right to be forgotten is built in, not a support ticket.
What Atlas does NOT do
Atlas does not train AI models on your data. Your conversations and memories are not fed into a training pipeline. Atlas does not sell your data to third parties. Atlas does not show advertising — the subscription model means the user is the customer, not the product. Atlas does not share your data with other users — ever. Your memories, vault, and conversations are invisible to everyone but you.
Third-party AI providers
When Atlas thinks, it sends your message (plus the assembled context — personality, relevant memories, vault snippets) to an AI provider: OpenAI, Anthropic, or Google. Each provider has its own privacy policy governing how they handle API inputs. On the Free and Pro tiers, Atlas uses its own provider keys, so your prompts are sent under Atlas's API account. On the Enterprise tier, BYOK (Bring Your Own Key) lets your team supply its own provider keys — your prompts go directly to the provider under your own account, never touching Atlas's billing or infrastructure.
read: only the creator). Passcode locks: SHA-256 hash, client-side verification, plaintext never stored. Vault sharing: granular access grants with view/comment/edit levels, revocable. BYOK: user-supplied provider keys passed directly to the provider (Enterprise tier). No model training on user data. TLS in transit, managed encryption at rest. GDPR/CCPA-aligned: access, rectification, erasure, portability all supported.Atlas in your life
Atlas connects to your Google workspace through OAuth — Gmail, Calendar, Drive, and Sheets. Once authorized, it can read your inbox for commitments, look at your calendar to plan your day, save the documents it drafts to your Drive, and sync your tasks to Sheets. This is what turns Atlas from a chat window into an assistant that's actually in your life.
Why Atlas is not another chatbot
There are hundreds of AI assistants. Most are wrappers around a single model with a chat box. Atlas is fundamentally different — not in one way, but in eight. Each advantage below is structural, not cosmetic: it's how Atlas is built, not a feature bolted on. Together, they create a product that no generic chatbot can match today.
Every other AI forgets you when you close the tab. Atlas remembers you forever — across every device, every conversation, every year.
Generic tools use one model for everything — you overpay for simple questions and underpower complex ones. Atlas matches the brain to the task.
Long conversations on other platforms cost the same every turn. Atlas caches the stable prefix, cutting long-chat costs by ~90%.
When one AI provider goes down or hits a quota, other tools show you an error. Atlas silently switches to the next available brain.
Other assistants train on your data, show ads, or share it. Atlas locks everything to you, trains on nothing, and shows no ads — ever.
Chatbots live in a tab. Atlas reads your inbox, checks your calendar, saves to your Drive, and syncs tasks to Sheets — automatically.
Most tools are device-bound or require manual sync. Atlas is real-time across phone, laptop, and tablet — pick up where you left off, anywhere.
No other consumer AI assistant lets you use your own provider keys. On Enterprise, Atlas does — your prompts never touch our billing.
Simple, honest pricing
Atlas is commercialized on three tiers. Free runs on Google's free-tier AI to let people try it with zero friction. Pro unlocks the mid and premium brains, unlimited memory, all integrations, and cross-device sync — priced to cover the direct-API cost plus margin. Enterprise adds BYOK so teams bring their own AI keys, turning the subscription into pure software revenue insulated from high-usage customers.
From a reminder to a full week plan
The same engine handles a one-line reminder and a full week-planning pipeline. The difference is which tier fires, how much of your memory is loaded, and how many calls chain together.
A day with Atlas
You wake up. Atlas has already scanned your inbox and calendar overnight and generated a morning briefing — your commitments, your open items, and what matters today.
You ask Atlas to help draft a tricky email to your landlord. Tier selector picks standard. Your memories about your housing situation are loaded. Atlas drafts it in your tone, cached.
A quick follow-up goes to Google (light tier), but the free tier just hit its per-minute limit — 429. Failover silently retries on OpenAI. You never see an error.
You ask Atlas to plan your week. Deep tier: Opus, your full memory, your calendar, your inbox scan. It creates open items for each commitment and a weekly plan in your vault.
You open a passcode-locked conversation about something personal on your phone — the one you started on your laptop this morning. It's all there, instantly, and locked behind your code.