Analysis updated 2026-05-18
Automatically extract and save team trial scores from Umamusume match screenshots posted to Discord.
Analyze score distributions for your team using built-in summary and chart commands.
Correct OCR misreads on individual records without losing the rest of your stored data.
Export your full score history as CSV files for further analysis in a spreadsheet.
| jsntm/umatt_discordbot | a-bissell/unleash-lite | abhiinnovates/whatsapp-hr-assistant | |
|---|---|---|---|
| Stars | 1 | 1 | 1 |
| Language | Python | Python | Python |
| Setup difficulty | moderate | hard | hard |
| Complexity | 3/5 | 4/5 | 3/5 |
| Audience | general | researcher | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires a Discord bot token and optionally an OpenAI API key, EasyOCR or Tesseract needed if skipping OpenAI.
This is a Discord bot designed for players of Umamusume, a Japanese mobile game about horse-girl racing. Specifically, it helps players who participate in team trials, a competitive mode where you build a team and track scores across multiple rounds. The bot automates a process that players would otherwise handle manually: reading score numbers from in-game screenshots and organizing them into structured data. The core feature is OCR, which stands for optical character recognition, the technology that reads text from images. After a team trial match, a player takes two screenshots of the results screen, one of the top portion and one of the bottom, then sends both to the bot via Discord slash commands. The bot extracts the numerical scores from those images and saves them as CSV files on the host machine. By default it uses OpenAI's vision model for this, but it also falls back to two open-source alternatives, EasyOCR and Tesseract, if no API key is available. Once scores are recorded, the bot offers analysis and editing commands. Players can view a statistical summary of their team, generate a box-and-whisker chart of score distributions, and export their data as CSV files. If the OCR reads a number incorrectly, correction commands let a player replace, add, or delete specific records without starting over from scratch. Data is stored locally in a folder organized by Discord user ID, so multiple players can share the same bot instance without their records mixing. The folder can be copied to preserve data between restarts or when moving the bot to a different machine. Running the bot requires Python, a Discord bot token, and optionally an OpenAI API key for better OCR accuracy. The README's setup instructions are written for Windows, though the underlying Python code is not inherently platform-specific.
A Discord bot for Umamusume players that reads match scores from screenshots using OCR and tracks team trial statistics.
Mainly Python. The stack also includes Python, Discord.py, OpenAI API.
No license information is stated in the README.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly general.
This repo across BitVibe Labs
Verify against the repo before relying on details.