ONIOKO Beta
Blog Technology SDK & API
EU AI Act join@onioko.com
Human Preservation

Everything Records You. Nothing Knows You.

ONIOKO preserves the living human: Perceived in the moment, remembered over time, measured only against yourself. Preservation starts with your first conversation.

Build with it → Preserve a person
Perceived in the moment
Remembered over time
Never measured against anyone but you (EU AI Act aligned)
Perception
Sees what the eye can't. In the moment.
Memory
Keeps what the brain won't. Over time.
Consent
Deletion that actually deletes.
Scroll
02 · The Turn

Every machine can see you. Not one of them knows you.

Capability
03 · The Capability

The engine, available today.

Perception in the moment. Memory over time. Pointed at the human, not the data.

Developers
SDK & API

A build surface teams can integrate, not a black box they have to buy whole.

Bring your own avatar, dashboard, companion, or research workflow. ONIOKO exposes the live perception loop, structured outputs, and the GLUE layer that turns them into stable API payloads and LLM-ready context.

Integration modes

Fit the pipeline to the runtime you already run.

Live systems rarely want one transport. Capture can come in over WebRTC, streams can stay on SSE, and delivery can hand off over WebSocket. The point is not to force our frontend. The point is to let your product keep its own surface.

WebRTC Capture ingest for live sessions
SSE Transcript, signal, insight, trace, and transport streams
WS Delivery relay for downstream avatar or application state
Current surface

The real-time API already maps to the working pipeline.

The current integration layer in the codebase exposes dedicated paths for capture, transcript, CYGNUS, ORACLE, LUCID, delivery, TRACE, and transport state.

Representative endpoint families
/api/realtime/capture
/api/realtime/transcript
/api/realtime/cygnus
/api/realtime/oracle
/api/realtime/lucid
/api/realtime/delivery
/api/realtime/trace
/api/realtime/transport
What teams receive

Structured for APIs. Readable for language models.

GLUE is the handoff layer between OPM and consuming systems. It can pass structured perception to dashboards and versioned clients, or turn the same stream into context a language model can actually use during a live turn.

Discuss integration See GLUE

Best fit for avatar systems, live companions, coaching tools, research workflows, and customer products that need perception without rebuilding their stack around someone else's UI.

Structured signals

Observable outputs, not mood labels: facial action units, prosodic features, posture dynamics, and cross-channel findings.

LLM-ready context

Formatted summaries and context blocks for avatar turns, guidance systems, or downstream agent orchestration.

Bring your own interface

Use ONIOKO natively or embed the stack inside your own product, workflow, dashboard, or customer-facing experience.

04 · Where It's Used

The buyer who can pay today.

The perception and the memory ship as an engine. Anyone building something that faces a human can put it underneath.

05 · The Roof

Human Preservation.

06 · The Objections

The strongest conversion tool sits high.

The approved answers stay precise, bounded, and human-readable.

Proof
07 · The Proof

A direction, not a promise.

Everything records you. Nothing knows you. We're changing the second half, and we'll show our work.

08 · Go Deeper

Extended Humans

Three doors, if you want to go further than a landing page can take you.

09 · CTA

Choose where preservation begins.

Two entry framings. One booking form.

Build with it → Preserve a person
FAQ

Common Questions

Questions serious buyers, partners and compliance teams actually ask before they adopt OPM in production.

No. Wearables are total capture: An always-on microphone records everything, including people who never agreed, and compares you against population averages. ONIOKO is chosen moments: Nothing to wear, nothing to charge, nobody recorded without asking. Perception happens only in conversations you choose, and you are measured only against your own normal.

No. The avatar is one head across four channels: Chat, voice message, video message, and video call. A text message is enough for the system to stay current with you. You choose the channel and the moment, every time.

Neither. Grief tech preserves the dead; digital twins build a copy that works in your place. We preserve the living, not a copy: The person who speaks today is seen and kept today, with consent, with revocation, with deletion that actually deletes.

No. OPM does not infer emotions or mental states. It detects observable signals and cross-channel congruence patterns. That distinction is exactly why education-safe and workplace-safe configurations can be deployed responsibly. Read the compliance documentation.

Never. The system reports observable expression and signal relationships, not hidden feelings. The final interpretation remains with the human professional using the instrument.

Emotion recognition tries to classify inner states from outer behavior. OPM stops one step earlier. It documents what is visible, measurable and crossmodally aligned or misaligned, without making the inferential leap.

In education, ONIOKO can be configured with CYGNUS and ORACLE only. LUCID and TRACE stay off, which prevents emotional profiling and longitudinal behavioral tracking of students.

Most configurations process video and audio in real time and retain only derived descriptors or approved observation outputs. Storage policies depend on the context, consent model and feature set.

Yes. CYGNUS and ORACLE are designed for live readouts, while specialized configurations such as CYGNUS Lite and ORACLE RT support faster-response deployment patterns.

Yes. OPM is modular. Some deployments stop at raw signal extraction and pattern recognition, while others activate contextual insight and longitudinal tracking only where appropriate.

That depends on the deployment contract, but the architecture is built so outputs, retention logic and access controls can be scoped tightly per customer, product and role.

Yes. The architecture is explicitly designed for explainability at the signal layer. Compliance teams can inspect what was detected, what was communicated, and what the system was never allowed to claim.

No. It is an observational instrument, not an autonomous authority. The human expert remains the decision-maker, interpreter and accountable actor.

Yes. OPM can power ONIOKO-native products or be embedded into customer-specific experiences, dashboards, coaching tools and research workflows.

That is exactly what the architecture layer is for. Different sectors can activate different modules, context presets and guardrails without changing the core observational logic.