One connected view · built from a real reef

See the whole reef.
Not just the latest reading.

ReeferVision brings water, equipment, livestock, care history, and visual observations into one operating view—so reef keepers can understand what changed, what needs attention, and what happened after they acted.

Join the Beta Waitlist See What ReeferVision Does ↓
Designed around existing reef systems Local safety stays local Founder-built in Australia

Why this exists

A reef is one living system.
Its story shouldn't be scattered.

01

Everything affects everything. Water chemistry, equipment, livestock, and maintenance all influence one another. A single reading rarely explains what is happening across the system.

02

The history gets lost. Test results, device status, photos, care tasks, and observations often live in different places—or only in the keeper's memory.

03

Better care needs context. The useful question is not only “What is the number now?” It is “What changed, what needs attention, and what happened after I acted?”

I began building reef.home because I wanted one place to understand my own reef—its water, equipment, livestock, and the work of keeping it healthy. ReeferVision grows from that idea: clearer day-to-day care first, with earlier warnings earned from real history over time.

What ReeferVision is building

One operating view
for the whole reef system.

ReeferVision is the connected layer around the reef you already run: one history for water, equipment, livestock, maintenance, and visual observations. The first telemetry path is working; intelligence layers will be added only as pilot evidence supports them.

Connected Reef History

The working foundation mirrors selected ATO and reference-temperature history from ReefWatch to Google Cloud. The product is designed to extend that timeline across water tests, equipment, livestock, care, and images.

working foundation · ReefWatch + outbound cloud path

AI Coral Vision

The planned vision pipeline will compare each colony with its own photographic history for changes in polyp extension, tissue colour, and recession. Pilot images will determine which changes can be detected reliably.

planned · Vertex AI vision · longitudinal pilot dataset

Predictive Alerts

Time-series models are designed to learn dosing rhythm, evaporation, and consumption rates, then flag meaningful off-trend behaviour. Pilot evaluation will measure warning time and false-alarm rate before performance is claimed.

planned · BigQuery ML baselines and forecasting

Guided Care Workflows

Planned workflows show how water tests, care tasks, livestock observations, and system history could stay together through the hands-on moments where context is easiest to lose.

product simulation · live-input validation pending

Interactive Digital Twin

A product simulation explores how wavemaker positions, lighting, and a camera view could become a 3D flow-and-light map before hardware is moved in the water.

product simulation · live-input validation pending

Fleet Intelligence

With explicit opt-in and enough validated systems, anonymised patterns could reveal shared equipment failures or consumable issues while keeping each tank's operating data isolated.

roadmap · opt-in cross-fleet anomaly research

Setup

Start with the reef you already run.
Add intelligence in stages.

Connect the system you trust

ReeferVision is designed to receive selected readings from supported local systems, sensors, and cameras through an outbound edge bridge—without replacing the controller or safety rules already protecting the aquarium.

supported integrations · outbound-only design · local safety remains authoritative

Build one useful history

Water readings, equipment state, maintenance events, livestock observations, and repeatable images form a single timeline. Over time, the reef becomes its own reference instead of a collection of disconnected snapshots.

first telemetry path working · broader sources in validation

Earn better warnings over time

As baselines are validated, meaningful drift, stress, or equipment anomalies can become explainable alerts with the relevant history attached—so the reef keeper still decides what to do.

roadmap · measured baselines · human decision first

Development journey · real evidence

Built from a real reef,
one working layer at a time.

These are Peter's actual development images, not renders: the reef that made the problem personal, live sensor checks showing what is connected, and the working reef.home dashboard that brings the system together.

Peter's reef aquarium illuminated blue at home
01 · The reef

The reef that started it

Peter's reef tank at home—the real environment that inspired ReeferVision and became its first validation setting.

ReefWatch Sensors and checks screen showing live server, telemetry, temperature, ESP32, top-up power, input monitor, and safety states
02 · The live inputs

Sensors become visible and testable

The real Sensors & checks view exposes the ReefWatch server, tank telemetry API, canonical temperature, ESP32 commissioning state, top-up power, input monitors, and control-output safety. It is read-only by design.

Real reef.home diagnostics · read-only checks
Updated ReefWatch reef.home dashboard showing the live reef camera, maintenance plan, quick actions, and water parameters
03 · The operating view

reef.home brings the system together

The updated dashboard combines the live reef camera, current system, care plan, quick actions, and water parameters in one operating surface.

Real reef.home dashboard · August 2026 development state

Development note: these screenshots show a system still being commissioned, including incomplete and test inputs. They are evidence of what is running—not a polished production interface or an installation guide.

Real-world evidence · founder reef

From reef.home to Google Cloud, without handing over control.

reef.home is Peter's local ReefWatch operating layer. ReeferVision grows outward from that system, beginning with an outbound-only copy of selected telemetry rather than exposing the home service to the internet.

What this journey provedSelected ATO and reference-temperature history can move through an implemented, signed cloud path while aquarium control and safety remain local.

reef.home

ReefWatch remains the local view for Peter's water, equipment, livestock, schedules, and care.

Outbound bridge

The hub queues selected ATO and aquarium-temperature readings and authenticates each batch.

Cloud evidence

Cloud Run validates accepted batches and BigQuery stores the pilot history for analysis.

Safety boundary

There is no inbound cloud control route. Camera histories, baselines, and useful alerts remain the next validation work.

Clear boundary: this is founder-development evidence, not a claim of model accuracy or improved coral growth. The public dashboards below are sample-data product simulations and do not expose Peter's private reef telemetry.

Review the founder-pilot evidence →Explore the product simulation ↓

How it all works

Start with a read-only path.
Add intelligence when it earns trust.

The founder pilot implements the first narrow path: ReefWatch → outbound hub → Cloud Run → BigQuery. Every later stage below is roadmap unless explicitly labelled working now.

Working now · local source + queue

The outbound hub reads allowlisted ATO and reference-temperature history from ReefWatch and keeps unsent readings on disk. It cannot control aquarium equipment.

persistent local queue · allowlisted reads · no inbound control

Working now · signed cloud ingestion

The hub signs outbound batches for Cloud Run. Validated ATO and reference-temperature telemetry is written to BigQuery; camera storage and an event backbone are later stages.

HMAC-signed batches · Cloud Run · BigQuery

Roadmap · per-tank models

After repeatable image capture and labelled history exist, vision and time-series models will be evaluated against each tank's own held-out history.

planned · Vertex AI vision · BigQuery ML baselines

Roadmap · evidence-backed alerts

Only validated outputs would become graded alerts, with the relevant trend, frame, and confidence attached so an operator can decide what to do.

planned · Firebase live state · notifications

Roadmap · bounded automation

Automation is not part of the read-only pilot. Any future command would be tightly bounded and independently checked by local safety rules before equipment could respond.

future research · local safety remains authoritative

Product demo · sample data

It's not just the display tank.
It's the whole water system.

A reef is a chain of processes — RO production, mixing, quarantine, top-off, the display itself. A crash can start anywhere in that chain. This interactive simulation shows the intended whole-system operator experience; the values are representative sample data.

RO/DI Station
STN-01 · 4-stage + DI
Producing

Where every drop starts. ReeferVision tracks TDS in and out, membrane pressure, and production rate — and learns when your DI resin or membrane is on the way out.

TDS in
187ppm
TDS out
0ppm
Output
2.1L/h
Filtered tank
82%
Waste tank
34%
Membrane
62psi
TDS out · 30 daysresin depletion curve emerging

simulated model output: membrane rejection normal · DI resin at ~78% capacity, replacement forecast 6–7 weeks · filtered tank covers ~5 days of top-off · waste tank empty reminder at 85%

Salt Mix Vat
STN-02 · 100 L mixing reservoir
Ready

Water change water, monitored while it mixes and brought to match the display before it ever touches your tank. No more guessing whether the batch is ready.

Salinity
1.0255sg
Temp
25.9°C
pH
8.3
Vat level
88%
Salt stock
4.2kg
Buy salt in
23days
Salinity · 14 h mix cyclereached target, holding

simulated model output: batch matched to display, safe to transfer · salt consumption learned from your water-change rhythm · reorder reminder lands ~5 days before you'd run out

Quarantine / Hospital Tank
STN-03 · 75 L bare-bottom QT
Watch

QT systems are unstable by design — small volume, no mature filtration, medicated water. The vision model scores corals in treatment, and the float valve gets cleanliness tracking, because a gunked-up QT float is how hospital tanks overflow.

NH₃
0.05ppm
Temp
26.0°C
Salinity
1.0250sg
Coral health
87/100
Float clean
71%
Clean due
6days
NH₃ · 48 hslow rise since yesterday's feeding

watch item: trace ammonia rising since yesterday's feeding · suggested: small water change from matched mix vat (STN-02) · coral in treatment trending up from 79 over 8 days · float clean scheduled with next water change

Top-Off & Fill Process
STN-04 · ATO reservoir + transfer pump
Nominal

The quiet failure point in most systems. ReeferVision tracks reservoir level, fill events, and pump behaviour — a stuck float valve looks very different from normal evaporation, and the model knows it.

Reservoir
64%
Evap rate
1.9L/d
Fill events
11/24h
Reservoir level · 7 daysrefill sawtooth, normal cadence

simulated model output: fill cadence matches learned evaporation curve · reservoir lasts ~8 more days · refill reminder scheduled

Sump & Filtration
STN-05 · sump, skimmer, return · whole-of-system maintenance
Nominal

The engine room. Sock loading, skimmer behaviour, and return pump draw all have learned signatures — and every serviceable part in the system gets a maintenance clock, so cleans and seal replacements happen on schedule instead of after a failure.

Sock loading
86%
Sump level
22.4cm
Skimmate cup
41%
Return pump
41.2W
Return flow
3400L/h
Skimmer air
9.4L/m
Sock loading · since last changerestriction building, change soon
Maintenance clocks · whole of system
Filter sock changedue in 2 days
Skimmer cup & neck cleandue in 5 days
QT float valve cleandue in 6 days
Return pump impeller cleandue in 3 weeks
Probe recalibrationdue in 5 weeks
Pipe seals & O-ringsreplace in 4 months

simulated model output: clocks aren't fixed timers — sock loading is read from the level differential across it, and the schedule adjusts to how your system actually fouls

The intended alert experience: graded, with the evidence.

This simulated phone view demonstrates how overflow restrictions, leaks, stuck floats, and drain blockages could be presented after the alert models are validated:

  • WatchSomething's drifting. Logged and tracked — no action needed yet, but the model is paying closer attention.
  • WarnIntervene soon. A trend is heading toward a threshold. You get the chart, the camera frame, and the likely cause.
  • ActRight now. Flood-risk and livestock-risk events. Future bounded automation could request a locally approved response; it is not part of the current pilot.

This product simulation cycles representative sample values so you can see the intended dashboard behaviour. The founder pilot uses real ATO and aquarium-temperature telemetry, but that private data is not displayed here. Future vision and prediction features remain clearly labelled until measured validation is complete.

Product simulation · planned workflows

Monitoring is half of it.
The other half is doing things right.

These screens demonstrate intended workflows and are not driven by founder-tank data. The goal is to support hands-on moments such as adding livestock and choosing where a coral goes.

Acclimation Assistant
New arrival · Acropora frag · started 12 min ago
In progress

In the intended product, a keeper would identify the new arrival and receive an acclimation plan based on validated live readings rather than a fixed timer.

  • ✓ Lights dimmed to 20% · flow pumps paused near arrival zone done
  • 2 Float bag — equalising temperature
    finishes when bag ΔT < 0.2°C, not on a fixed timer     11:42
  • 3 Drip mix — slow 1:1 water blend over ~40 min queued
  • 4 Placement — recommended spot ready (see tank map) queued
Bag ΔT
0.4°C
Drip rate
3.2mL/m
Bag salinity
1.0242sg

concept note: a future app could notify the keeper when each measured step is ready and save the completed workflow to the livestock record

Placement Advisor
Digital twin · flow & light map · concept render
Spot found

The concept combines wavemaker positions, lighting, and a camera view into a flow-and-light map, then explores placement guidance by species.

AUpper rock shelf — recommended for this Acropora. ~250 PAR · high indirect flow · in the crossfire of both wavemakers without direct blast, close to the light.
BMid rockwork. ~140 PAR · moderate flow · suits most LPS — hammers, torches, favia.
CShaded sand bed. ~60 PAR · low flow · mushrooms, zoas, and anything that sulks in current.

concept note: future live inputs could update the map after a pump or lighting change; PAR values shown here are fictional estimates and require physical calibration

Where this can scale

Start with demanding reef keepers.
Build toward managed living systems.

The first users provide dense feedback and diverse tank histories. The same monitoring loop can then serve operators responsible for many systems and higher-value livestock.

Commercial model under validation: subscription monitoring paired with an edge hub and camera module for serious reef keepers, followed by fleet plans for service businesses and coral aquaculture. Pricing is not final and will be tested with founding pilots before launch.

BEACHHEAD · 01

Serious reef keepers

High-value, sensor-rich home systems where avoidable failures are painful and owners already invest in monitoring and automation.

EXPANSION · 02

Aquarium service businesses

A fleet view for teams maintaining tanks across customer sites, with earlier intervention and auditable maintenance workflows.

PLATFORM · 03

Coral aquaculture

Multi-system operations where water chemistry, animal health, equipment performance, and intervention history must be understood together.

Open interactive digital twin Review technical architecture → Review pilot evidence →

Founder

Built from a reef keeper's
own operating problem.

Peter Skliros on the water

Peter Skliros

Founder · ReeferVision

ReeferVision began with a question Peter kept facing at home: what changed, what needs attention, and how do I keep the full history of a living system in one place? His own reef became the first place to build a practical answer.

Peter is proving the dependable data path first, then adding camera histories and measured warnings only when the evidence supports them.

Founding pilot · Expressions of interest

Help prove what actually prevents a reef failure.

ReeferVision is pre-launch. The founder-operated reef.home telemetry pilot has been established, and we are preparing a small external founding pilot to validate installation, collect paired image and telemetry histories, and learn which alerts are genuinely useful. There is no paid subscription today and no model-performance claim hidden behind this form.

Delivered privately by emailApplications go directly to Peter and are not stored in the website database.
Loading secure spam protection…

Collection notice: ReeferVision collects these details only to assess founding pilot interest. They are delivered to waitlist@reefervision.com.au through an email provider and retained in the receiving mailbox, not in a website database. Email that address to request access, correction, or deletion.

Or email waitlist@reefervision.com.au

Camera + hub module at our cost Founding pricing when plans launch Direct line to Peter, the founder building it