> ## Documentation Index
> Fetch the complete documentation index at: https://dingguoliang.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Projects: Voice Agent Platform and Notes

> Projects entry: desensitized flagship and real stack.

This section holds tellable case studies and engineering notes. The flagship is a desensitized edge voice-agent control platform.

***

## Flagship project

<Card title="Edge Voice-Agent Control Platform" icon="microchip" href="/en/projects/voice-agent-platform">
  Console + control API + on-device speech service in one loop. Past half-year focus; functionally closed and entering launch.
</Card>

***

## Stack (aligned with the flagship)

<CardGroup cols={2}>
  <Card title="Admin web" icon="desktop">
    **Vue** console, multi-region business APIs, permission-aware UI.
  </Card>

  <Card title="Control API" icon="server">
    **Java / Spring Boot**, MySQL, Redis; devices, agents, models, knowledge, team permissions.
  </Card>

  <Card title="Device service" icon="microchip">
    **Python / asyncio**, WebSocket sessions; VAD→ASR→LLM→TTS or end-to-end speech.
  </Card>

  <Card title="Retrieval and multimodal" icon="database">
    External knowledge/vector engines via adapters; ASR/TTS and vision-related capabilities.
  </Card>
</CardGroup>

***

## Engineering notes

<CardGroup cols={2}>
  <Card title="Lessons learned" icon="lightbulb" href="/en/notes/lessons-learned">
    Dual-mode config, session latency, permission layers.
  </Card>

  <Card title="LLM gotchas" icon="triangle-exclamation" href="/en/notes/llm-gotchas">
    Injection, hallucination, context, rate limits.
  </Card>

  <Card title="Performance tips" icon="gauge-high" href="/en/notes/performance-tips">
    Latency and throughput practices.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.