git404hub

what is hgdoll fr?

521xueweihan/hgdoll — explained in plain English

Analysis updated 2026-05-18

19KotlinAudience · developerComplexity · 4/5LicenseSetup · hard

tl;dr

HGDoll is an open-source Android app that watches your phone screen and listens to your voice to give real-time AI voice commentary while you play games.

vibe map

mindmap
  root((HGDoll))
    What it does
      Watches phone screen live
      Listens via microphone
      Real-time voice commentary
      AI gaming companion
    Tech stack
      Kotlin Android client
      Python FastAPI backend
      Doubao models
      Volcano Ark platform
    Use cases
      Live game commentary
      Self-hosted voice companion
      Vision-language demo
    Status
      Early proof of concept
      MIT licensed
      Actively improved

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

what do people make with this?

VIBE 1

Get real-time AI voice commentary and encouragement while playing mobile games on Android.

VIBE 2

Self-host the client and backend to build your own screen-aware voice companion app.

VIBE 3

Study a working example of combining screen capture, speech recognition, and vision-language models.

what's the stack?

KotlinPythonFastAPIDoubao

how it stacks up fr

521xueweihan/hgdollareu01or00/hermes-agent-mobile-clientdw2lam/openlauncher
Stars191918
LanguageKotlinKotlinKotlin
Setup difficultyhardmoderatemoderate
Complexity4/53/52/5
Audiencedeveloperdevelopergeneral

Figures from each repo's GitHub metadata at analysis time.

how do i run it?

Difficulty · hard time til it works · 1h+

Requires running both an Android client and a separate Python backend, plus API keys for ByteDance's Doubao models via Volcano Ark.

MIT license, free to use, modify, and self-host, including for commercial purposes.

in plain english

HGDoll is a fully open-source Android app that acts as an AI companion while you play mobile games. Instead of playing alongside you in the game itself, it watches your phone screen in real time, listens to you through the microphone, and responds with voice chat, commentary, and encouragement. Think of it as a friend sitting next to you who can see what you are doing and react to it. The app is split into two parts. The Android client, written in Kotlin, handles screen recording and speech recognition on the phone. It takes periodic screenshots and converts your voice to text, then sends both to a separate backend server. The backend, written in Python using FastAPI, receives that data, builds a running picture of the conversation context, and passes it to a set of AI models. One model looks at the screenshots to understand what is on screen, another generates a text response, and a third converts that response back into spoken audio that plays through the app. All of the AI processing relies on Doubao, a family of large language and vision models from ByteDance, accessed through the Volcano Ark platform. You need API keys for these services to run the project. Both the client and server can be run locally, and setup instructions live in their respective subdirectories. The project is described by its author as a small toy still full of bugs and rough edges, actively being improved. It is released under the MIT license, so anyone can read the code, run it, or contribute changes. If you want an AI that reacts to your gameplay in real time through voice, this is a working proof of concept you can self-host.

prompts (copy fr)

prompt 1
Walk me through setting up the HGDoll Android client and Python FastAPI backend locally.
prompt 2
Explain how HGDoll turns a screenshot and voice input into a spoken AI response using Doubao models.
prompt 3
What API keys do I need from Volcano Ark to run HGDoll, and where do I configure them?
prompt 4
How could I swap Doubao for a different vision-language model in this project's backend?

Frequently asked questions

what is hgdoll fr?

HGDoll is an open-source Android app that watches your phone screen and listens to your voice to give real-time AI voice commentary while you play games.

What language is hgdoll written in?

Mainly Kotlin. The stack also includes Kotlin, Python, FastAPI.

What license does hgdoll use?

MIT license, free to use, modify, and self-host, including for commercial purposes.

How hard is hgdoll to set up?

Setup difficulty is rated hard, with roughly 1h+ to a first successful run.

Who is hgdoll for?

Mainly developer.

peek the repo → explain another one

This repo across BitVibe Labs

double-check against the repo, no cap.