← Kioko · lens 5 / 5Switchboard · compare all 3 voices
One prompt · three personalities

One question.
Three answers.

WARM COMPANION · SOFT
HONNE

Send a prompt to see HONNE's reply.

UNFILTERED · GOONING · LATE-NIGHT
YAMI

Send a prompt to see YAMI's reply.

AGI · STRATEGIST · ANALYTICAL
SHIN

Send a prompt to see SHIN's reply.

Where they diverge
01Chapter 01 / 02Divergence

Where they
diverge.

Model choice, generation parameters, and steering — exactly as they were applied this turn.

Run a prompt above to see the live divergence.

How routing works
02Chapter 02 / 02Architecture

Why the outputs
actually differ.

This isn't prompt engineering. The divergence is structural — mode selection, memory scoping, model routing, and persisted steering all happen before the first token is generated.

01
Selection

Mode selected

The user chooses a personality — or the system infers one from context and time of day. This determines which voice, which memory vault, and which model will respond.

02
Retrieval

Memory scoped

Each mode retrieves only its own memories plus shared facts. HONNE sees companion cues. YAMI sees late-night confessions. SHIN sees strategic goals. No cross-mode leakage.

03
Model

Model routed

Different modes can use different LLMs. HONNE may run on GPT-4o for warmth. SHIN on Claude for precision. YAMI on Hermes for unfiltered output. Same character, different engine.

04
Adaptation

Voice adapted

Tone, length, formality, and directness are all mode-dependent. Steering values are persisted per mode and applied to the system prompt at generation time.

Pick your mode and start.

offline
waiting for her first turn…