The AI coworker
that lives in your inbox.
Email is where work happens. We made it where AI work happens. Triage the inbox, query your data, summon a microapp, automate the routine — and reach into the systems you already use. Runs in your browser, or on your own hardware with one docker-compose. Bring your own LLM key, or point it at a local model.
The Stripe failure is the 3rd from Acme this quarter — I pulled the others from your Postgres. Want me to draft a reply to Jane asking about payment method, log a refund-request entry, AND open a microapp to track future Acme charges?
Six capabilities. One companion.
Not a chat sidebar tacked onto an old app. A coworker that lives in every screen of the client, with access to your mail, your data, and the systems you've already paid for.
Email & chat-native AI
Triage your inbox. Draft replies in your voice. Summarize threads. Extract action items into a microapp or task. Message the same companion from WhatsApp or Telegram — one coworker, every channel you already use.
Data integration
Connect Postgres, MySQL, SQL Server, Oracle, Snowflake, BigQuery, Databricks, Redshift, MongoDB and more — 14 databases in all. Ask in plain English. The companion reads your schema first, runs read-only queries, and answers in words, a table, or a chart. One question can span two systems: it will read your warehouse and your document store and join them on the customer.
Summoned microapps
"Build me a refund tracker." Get a working app with forms, KPIs, dynamic tables, and one-click write actions. Pick from 5 hero templates or describe your own.
Legacy app integration
Reach into the SaaS apps you already pay for — Stripe, Slack, Teams, Salesforce, HubSpot. Read their data, write back, trigger workflows. No new tabs.
Task automation
Schedule the routine. Weekly customer digest. End-of-month finance close. Refund-decision queue checked every morning. The companion runs them, sealed and audited.
Knowledge + memory
Remembers what you've worked on, what your team has decided, what each customer prefers. Searchable knowledge base. Cryptographic audit chain on every action.
Plugs into what you already pay for.
Your databases. Your SaaS tools. Your LLM accounts. Your own hardware. Each connection is per-tenant, encrypted at rest. Writes are opt-in. Audit-sealed on every action.
- Per-tenant Fernet vault — keys never returned to client
- Read-only by default; writes require opt-in flag + DML-only gate
- Tamper-evident audit chain (ImmuDB-sealed) on every action
- MCP server — your agents are also callable from Claude Desktop, Cursor, any MCP client
Runs in your browser. Or on your own hardware.
One Flutter codebase targets every platform, and the web client is live today. Desktop and mobile builds are in the pipeline — we'll ship them when they're worth installing, not before.
Web Live
Sign in at app.oentity.org. Nothing to install.
macOS & Windows
In development. The desktop shell exists; signed, notarised installers do not yet.
iOS & Android
In development. Android builds today; neither is in an app store yet.
Self-host
One docker-compose. Your hardware. Your data. Your rules.
What a workday looks like with a companion.
Real jobs, start to finish — each one chains the same capabilities: read your mail, query your data, act in the tools you already pay for, and seal it in the audit chain. No prompt engineering required.
Chase every failed payment
"Any Stripe charges bounce this week? Who, how much, and is it a repeat?"
- 1 Pulls failed charges from Stripe, cross-checks history in Postgres
- 2 Drafts a dunning email in your voice, flags 3rd-strike accounts
- 3 Summons a refund tracker microapp for the repeat offenders
Outcome: recovered revenue queue, ready before your coffee's cold.
Never drop a warm lead
"Watch the inbox — surface anything that smells like a buying signal."
- 1 Triages inbound mail, scores intent, enriches from your CRM
- 2 Pings you on WhatsApp with a one-line brief + suggested reply
- 3 You reply "go" — it books the follow-up and logs the deal stage
Outcome: zero warm leads cooling in an unread inbox.
Monday metrics, on autopilot
"Every Monday, send me last week's numbers with what changed and why."
- 1 Runs read-only SQL across Postgres + Google Sheets on schedule
- 2 Builds the charts, writes the narrative — what moved, week over week
- 3 Emails the digest and posts it to Slack — sealed in audit
Outcome: the weekly report writes itself while you sleep.
Turn a spreadsheet into a tool
"Make my onboarding checklist a real app the whole team can use."
- 1 Reads your Google Sheet, infers fields, statuses, and owners
- 2 Generates a microapp — forms, KPIs, filters, write-back buttons
- 3 Shares it across web, desktop, and mobile — no deploy step
Outcome: an internal tool in a minute, not a sprint.
Describe the job in plain language. The companion picks the tools, the data, and the model — you don't wire anything.
Pay only for the AI you actually use.
Every plan includes a monthly token allowance — go over and you're billed by the token, never by the seat. Bring your own LLM key and those turns are free. Run a local model or self-host for zero LLM spend.
What does a token buy?
A "turn" is one question and everything the companion does to answer it — reading your schema, running the queries, building the chart. Measured on the live platform:
So the free tier's 2M is roughly a hundred real questions a month — enough to put this in your actual week, not just evaluate it. Paid plans are not about volume so much as which model answers: Growth and above run on the smarter tier, which costs us about twelve times as much per question. And if you connect your own OpenAI or Anthropic key, nothing is metered at all, on any plan.
You never pick a model. Your plan does.
Knowledge workers shouldn't have to know GPT from Gemini. Every plan maps to a capability tier — and the companion always uses the best one your plan allows. Pay more, quietly get a smarter model. Need a specific one? Premium plans can pin it.
The free tier is live and self-serve — sign up and the 2M monthly tokens are yours, no card. Paid plans are priced and metered but not yet purchasable; we'll open them when checkout is ready. Start free →
- ✓ 2M tokens / month — about 100 questions
- ✓ 1 mail account · 1 data source
- ✓ Standard model tier
- ✓ Web client
- ✓ Or bring your own key — free turns
- ✓ 4M tokens / month — on the smarter model
- ✓ 5 data sources · 5 seats
- ✓ Priority on new channels
- ✓ Standard + Advanced models
- ✓ Email support
- ✓ 10M tokens / month
- ✓ Unlimited data sources & seats
- ✓ All channels — Telegram, WhatsApp, email
- ✓ All models incl. Premium + model pinning
- ✓ Audit trail · priority support
- ✓ Volume token allowance
- ✓ Unlimited everything
- ✓ SSO / SAML · audit export
- ✓ SLA · dedicated CSM
- ✓ Self-host option
Today, one companion. Next, a team of them.
The coordination layer that lets agents collaborate is already running under the hood — a durable event bus carrying every channel message, schedule, and audit event. Here's what we're building on top of it.
Agent-to-agent collaboration
A roster of specialist agents — Inbox, Data, CRM — each with its own focus, handing work to one another autonomously over the event bus instead of one companion doing everything.
Microsoft 365 & Gmail OAuth
One-click mail connect for the accounts your team already lives in — no app passwords, no IMAP setup.
SSO & high availability
SAML single sign-on, audit export, and a highly-available multi-node deployment for teams that outgrow a single box. Warehouse connectors shipped — Snowflake, BigQuery, Databricks and Redshift are live today.
Your inbox is where work happens.
Make it where AI work happens.
Knowledge workers and a new generation of doers deserve a coworker, not a chatbot. Sign up free — no card. Bring your own model, or pay only when you use it.