Private AI
FAQ

Working private prototype

A private AI operating layer for your life.

For people who want an AI system that remembers, coordinates, and stays under their control, with a personal operating system live and working in the background.

Discuss further See how it works
The idea

Not another chatbot. A personal system that works where life already happens.

This is a working pilot of a private personal operating system with long-term, source-backed memory. It connects knowledge and actions across the tools a person or family already uses, while keeping the system readable, inspectable, and portable.

How it works

Three ideas make it different.

01

It remembers from sources

Important facts come from real notes, records, tasks, and logs. They remain traceable to their source instead of disappearing into vague conversational memory.

02

It coordinates across life

Focused assistants connect personal administration, family and travel, household and finance, the connected home, and the flow of information between them.

03

It keeps the owner in control

Access is scoped by task. Durable memory requires human approval, sensitive actions keep a confirmation step, and the knowledge remains readable outside any one AI model.

Seen in the system

It remembers from sources, and the sources are connected.

Facts come from real notes, records and logs rather than from conversational memory. Each answer stays traceable to the file it came from, and the files reference one another.

Every bar in these captures is a deliberate redaction, not a rendering fault. What gets withheld follows a written disclosure rule, decided once, rather than a judgement call made page by page.

Live knowledge map Recorded from the working system
Real system recording
The whole knowledge base
  1. 01
    The whole knowledge base

    Every dot is a note. Dense clusters are subjects with deep, connected material behind them.

  2. 02
    Zoom into the relevant neighbourhood

    Moving closer makes individual pages legible while keeping the relationships around them visible.

  3. 03
    One page, with its connections intact

    Selecting a page reveals the frameworks, plans and references around it, so an answer remains traceable.

View the original still captures
A close view of the note graph centred on a pricing note and its connected frameworks.
One note and the sources connected to it.
The whole note graph, with several thousand notes joined by reference lines.
The full knowledge map.

Where it helps

One operating layer across the parts of life.

Personal administration

Inbox, calendar, tasks, documents, decisions, and project continuity.

Family and travel

Shared planning, groceries, trips, chores, allowance, and family coordination.

Household and finance

Vendors, receipts, payments, shared expenses, and recurring follow-ups.

Connected home

Lights, scenes, sensors, cleaning, watering, alerts, and household routines.

Health

Health records, test results, and history kept connected, organized, and searchable.

Seen in the system

It runs the house it lives in.

The connected home is part of the same operating layer, not a separate hobby. This real phone walkthrough moves from the whole house to one room, a shared occasion and the watering system underneath it.

Live home control Recorded from the working system
Real phone recording
The whole house at a glance
  1. 01
    The whole house at a glance

    Rooms and devices are grouped by floor, so the system understands where an instruction belongs.

  2. 02
    One room, direct control

    Lights, blinds, climate and media remain available in one place when direct control is useful.

  3. 03
    A moment, not a device list

    Entertaining brings the living room, kitchen, entrance, staircase and gate into one useful view.

  4. 04
    The infrastructure underneath

    Watering totals, valve state, flow and missed-run alerts are visible when the family needs the detail.

View the original redacted home captures
A home dashboard listing rooms by floor across four levels, with two private room labels covered by opaque redaction bars.
Four levels, grouped into one readable map.
A home dashboard grouping shared-space controls for entertaining.
Shared-space controls grouped around entertaining.

Watching and raising the flag when needed

The interface is only half the point.

The system confirms scheduled work, keeps reading the sensors and raises an exception without waiting for someone to inspect a dashboard.

Garden monitor Automatic
06:03
Morning watering completedSoil moisture increased by 2%
Done
13:03
Afternoon watering completedSoil moisture increased by 2%
Done
13:45
Soil moisture: 98%Still unchanged after both cycles
Watch
Possible leak or stuck waterThe system raised this alert on its own.
The morning cycle completed
An alert nobody asked for. It confirms the work, notices an abnormal reading and sends the exception to the family.
View the original redacted alert
The original irrigation report confirming two watering cycles, then warning of a possible leak.

Works where the family already communicates

It travels with the family.

There is no new app for the family to learn. The assistant joins the WhatsApp group everyone already uses, so questions, updates and shared decisions stay visible to the whole group. It answers questions, writes briefings and keeps watching the bookings.

Choose a real trip story

etgar.ai

✈️ Flight update

According to TriFlight and Trip.com, the current schedule is:

  • Departure: 14:30 Dubai time, Terminal 3
  • Arrival: 19:45 Colombo time, Terminal 1

The trip file says 15:00, so departure is 30 minutes earlier. The terminals are unchanged.

✓✓

What happened behind the message

01
Background check

The booking stayed under watch after the planning was finished.

02
Sources compared

Two flight trackers were checked against the time stored in the trip file.

Verified change15:00 → 14:30Terminals unchanged
The booking stayed under watch

Recreated from real exchanges. Names and personal details have been removed.

Open the original, redacted WhatsApp chats from the trip group
The original redacted flight-change message. The original redacted destination question and answer. The original redacted next-day trip briefing.

Works where the family already communicates

It settles the family's small economy.

The family reports chores in the WhatsApp group they already share, where everyone can participate and see the result. The price list is fixed in advance, so what a job is worth is not renegotiated at the end of the week.

Child

@etgar.ai I unloaded the dishwasher and loaded it again. 🍽️ Please add both.

✓✓
etgar.ai

I matched “Unload the dishwasher,” but “load the dishwasher” is not a standalone task in the fixed chore list.

Did you mean “Clear the sink and load the dishwasher,” or is this a new chore?

✓✓
Child

Yes. I cleared the sink and loaded the dishwasher. 👍

✓✓
etgar.ai

✅ Unload the dishwasher: +15 points
Weekly total: 35 points.

✅ Clear the sink and load the dishwasher: +15 points
Weekly total: 50 points. 🎉

✓✓

What happened behind the conversation

01
Fixed list checked

“Unload the dishwasher” matches. “Load the dishwasher” alone does not.

02
No guessing

An unknown phrase stops the process until the family clarifies it.

03
Exact match

The clarification maps to “Clear the sink and load the dishwasher.”

Ledger updated+15   +15Weekly total recalculated
A child reports two completed chores
Pocket money, and an assistant that refuses to guess. The familiar chat is only the surface. The important part is the rule-following behind it: verify the wording, ask when uncertain, then update the ledger deterministically.

Recreated from a real family exchange. Names and personal details have been removed.

Open the original, redacted WhatsApp chat from the family chores group
The original redacted request for two chores. The original redacted reply asking for clarification. The original redacted corrected request. The original redacted point awards and weekly total.

Working proof

Capability, reliability, and governance are already running together.

Capability
  • Daily use through WhatsApp and Telegram, in English and Hebrew
  • Focused agents for travel, groceries, chores, allowance, and finance
  • Source-backed memory plus connected tools and home systems
Reliability
  • Nightly deterministic self-audits and canary checks
  • Fallbacks across AI providers, with outage and recovery alerts
  • Nightly offsite backups, a recovery runbook, and an incident log
  • Watchers detect critical file replacement, session failures, and intrusion events, repair recoverable states, and alert when attention is needed
Governance
  • Specialists receive only the tools their job needs
  • The chores agent cannot inspect family photos because image access is not available to it
  • Long-term memory, usage, and cost are reviewed on a defined rhythm

Multiple models, one governed system

Model choice stays flexible. Usage stays visible.

Requests can move between providers when needed, while usage and cost remain measured by provider and every fallback stays visible. Subscriptions carry the work. Metered API billing is used only where no plan covers the job, which keeps it a deliberate exception instead of the default.

A status dashboard showing Claude and Codex plan consumption. Each plan has a session and a weekly bar, a mark showing where a flat burn through the window would stand, and a projection of where the current rate lands by reset. Below are gauges for backup freshness, vault size, disk, memory, CPU load and sync peers.
Plan consumption is visible too. Session and weekly limits are tracked before they become blockers.
AI usage Daily report

Estimated model cost today

$0.088
Primary provider$0.049
Secondary provider$0.038
Trailing 7-day average$0.224 / day

Fallback visible The last request used the backup model.

Usage is measured by provider
Cost is a governed number, not a surprise. Daily spend is measured against a trailing average, and a provider fallback remains visible when it fires.
View the original redacted report
The original redacted daily AI cost report.

Seen in the system

It watches itself, and says so when something is wrong.

A health panel regenerates through the day across both the knowledge base and the machine underneath it. Alerts fire only on red, plus one message when a fault clears, so silence is meaningful.

A status dashboard showing green checks for the knowledge base and its machine, plus one failed service in red. Product names, a service name, an address and an internal path are covered by opaque redaction bars.
The health panel, mid-day. Backup freshness, credential checks, scheduled jobs, disk, memory, load and connectivity stay visible in one report. Here, one service is red while the rest remains healthy. That is when a WhatsApp alert fires, followed by one recovery message when the fault clears.
Trust by design

Private enough to use. Inspectable enough to trust.

The operating system and its readable knowledge base run on a private home server. External AI models are interchangeable services, not the owners of the system or its memory.

Checks, incidents, and fixes remain visible. When a failure repeats, it is turned into a rule or a deterministic tool so the same problem is less likely to happen again.

Who is behind it

Built and operated by Etgar Bonar, a commercial executive who chose to learn AI by building and running a working system around real life.

He also built a mobile development workspace so he can inspect, program, and improve the system from anywhere.

Private conversations

Where could a private AI operating layer remove friction from your life?

Tell me what interests you