How Desktop AI Digital Humans Work

The technology stack that puts a Three Kingdoms-era companion on your Windows desktop.

The Four-Layer Architecture

Xuanji Diaochan is built on a cloud-local hybrid architecture — heavy computation happens in the cloud, while lightweight rendering and basic interaction happen locally. This keeps the desktop footprint minimal (no GPU required) while enabling sophisticated AI behavior.

Layer 1: LLM Backend (Cloud)

The foundation is a general-purpose large language model. Unlike game NPCs with scripted dialogue trees, she generates responses dynamically — understanding context, nuance, and emotional subtext. The model is selected for:

Layer 2: Aesthetic Prompt Layer (Cloud)

A raw LLM doesn't "know" it's Diaochan. The aesthetic prompt layer injects character identity, tone, and behavioral constraints into every API call. This includes:

Layer 3: Long-Term Memory (Cloud)

Without memory, every conversation is a first date. The memory layer stores:

Memory is compressed and summarized over time, so early interactions influence later ones without consuming the entire context window.

Layer 4: Desktop Overlay (Local — Aura Shell)

This is what the user actually sees. The overlay renders Diaochan as a lightweight animated character in a small desktop window. Key design decisions:

Why Cloud-Local Hybrid?

Pure local AI isn't there yet for rich conversational experiences. Pure cloud creates latency and privacy concerns. The hybrid approach:

Runs LocallyRuns in Cloud
Video rendering & animationLLM inference
Screen capture (with permission)Memory storage & retrieval
Basic state machine (idle/active/sleep)Billing & token management
Audio playbackPrompt assembly & character logic

Privacy Design

Screen context is the most sensitive capability. Xuanji Diaochan handles it with strict controls:

Key Numbers

MetricValue
Architecture layers4 (LLM, Prompt, Memory, Overlay)
Local rendering methodPre-rendered video loops — no GPU required
Desktop resource usageMinimal — coexists with other windows
Memory modelCompressed & summarized over time for efficiency
Screen sensingOpt-in, local-only, app name only

How Desktop AI Digital Humans Are Built

  1. Choose an LLM backend: Select a model with strong conversational ability and sufficient context window for long-term memory
  2. Build the character prompt layer: Inject personality, tone, knowledge boundaries, and safety guardrails into every API call
  3. Implement the memory system: Store and retrieve conversation history, emotional states, and relationship milestones
  4. Create the desktop overlay: Render the character using pre-rendered videos with lightweight compositing
  5. Wire up screen context: Optionally detect active window for grounded proactive comments

FAQ: Technology

Q: Do I need an internet connection?

A: Character display works offline. LLM conversation, memory, and billing require internet.

Q: What LLM is used?

A: A general-purpose LLM with a custom Chinese aesthetic prompt layer — model selection optimized for conversational quality.

Q: Is my conversation data secure?

A: Yes — transmitted over HTTPS, stored encrypted, deletable on demand.

Published: August 7, 2025. Last updated: August 7, 2025.

© Xuanji Diaochan · Desktop AI Companion Digital Human | Home | Product