explaingit

wess09/azurpilot

Analysis updated 2026-06-24

32PythonAudience · generalComplexity · 4/5Setup · hard

TLDR

Fork of AzurLaneAutoScript that automates the mobile game Azur Lane via screenshot OCR and taps. Adds 34 features, GPU OCR, an MCP server, and an LLM crash explainer.

Mindmap

mindmap
  root((AzurPilot))
    Inputs
      Emulator screenshots
      Game config
      MCP commands
    Outputs
      Tap actions
      Logs
      OCR text
    Use Cases
      Auto play Azur Lane
      Schedule farming runs
      Drive from AI agent
    Tech Stack
      Python
      PaddleOCR
      ADB
      MCP
Click or tap to explore — scroll the page freely

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 build with it?

USE CASE 1

Run unattended daily Azur Lane farming on an Android emulator with auto-restart on crash

USE CASE 2

Open equipment boxes by quantity and run island-plan or Big World dispatch on a schedule

USE CASE 3

Drive AzurPilot from an external AI agent through its 18-tool MCP server

USE CASE 4

Have an LLM read a crash log and suggest a fix via the built-in error analyser

What is it built with?

PythonPaddleOCRADBMCPCUDA

How does it compare?

wess09/azurpilotautolearnmem/automemcortex-ai-network/crypto-arbitrage-bot-automated-trading
Stars323232
LanguagePythonPythonPython
Setup difficultyhardhardmoderate
Complexity4/55/52/5
Audiencegeneralresearchergeneral

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

How do you get it running?

Difficulty · hard Time to first run · 1day+

Needs an Android emulator with ADB, a tuned Azur Lane configuration, and image recognition that breaks if skins or gear cover the UI.

In plain English

AzurPilot is a fork of AzurLaneAutoScript, a Python tool that plays the mobile game Azur Lane automatically by reading screenshots of the game and tapping the right buttons. The forked version keeps the original behaviour and adds features that were scattered across several community side-branches, plus some new experimental ones the author wrote on top. The README is upfront that most of the code was written or assisted by AI tools and that bugs are expected. Users are invited to send pull requests when they spot something wrong. The project also says some features are still experimental and recommends backing up the configuration before turning them on. A long checklist tells the player what to change inside the game itself before running the script, because the automation relies on image recognition. Suggested in-game choices include 60 FPS, automatic story playback at fastest speed, sleep mode turned off, and several toggles inside the combat menus. The README warns that custom skins, equipped gear, or decorations that cover the interface can confuse the screen reader. The list of additions compared to the original project covers about 34 items. Examples are island-plan automation, intelligent dispatch in the Big World mode, equipment-box opening by quantity, a fresh OCR text recognition model, customisable task priorities, GPU-accelerated inference on Windows or macOS, a first-run setup wizard, automatic restart of the Android emulator if the game crashes or ADB disconnects, scheduled emulator restarts, remote SSH command execution, log backup with compression, and an LLM-powered error analyser that asks a large language model to explain a crash. AzurPilot also exposes an MCP (Model Context Protocol) server with 18 tools, so an external AI agent can list instances, start or stop them, run individual tasks, fetch logs, take screenshots, update settings, or restart the emulator. The OCR text recognition model is custom-trained on PaddleOCR, with stated accuracy figures around 97 to 99 percent for Chinese and English game text. The download link, a companion launcher app for Windows and Mac, and a donation link are also provided.

Copy-paste prompts

Prompt 1
Install AzurPilot on Windows, point it at a fresh BlueStacks instance, and walk through the first-run setup wizard.
Prompt 2
Set the in-game toggles AzurPilot needs (60 FPS, fastest story, sleep off, combat toggles) before the first script run.
Prompt 3
Connect AzurPilot's MCP server to Claude Desktop and list the 18 tools it exposes.
Prompt 4
Enable GPU-accelerated PaddleOCR on macOS and verify OCR accuracy on Chinese and English game text.
Prompt 5
Configure scheduled emulator restarts and remote SSH command execution so I can babysit the bot from a phone.

Frequently asked questions

What is azurpilot?

Fork of AzurLaneAutoScript that automates the mobile game Azur Lane via screenshot OCR and taps. Adds 34 features, GPU OCR, an MCP server, and an LLM crash explainer.

What language is azurpilot written in?

Mainly Python. The stack also includes Python, PaddleOCR, ADB.

How hard is azurpilot to set up?

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

Who is azurpilot for?

Mainly general.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.