James4Ever0/vimgolf-gym

OpenAI gym style Vimgolf environment and benchmark for AI

31
/ 100
Emerging

This project helps developers evaluate AI agents designed to solve Vimgolf challenges. It provides a standardized environment to input an AI agent's Vimgolf key sequence, simulates its execution within Vim, and then outputs whether the challenge was solved correctly along with the agent's score. AI researchers and developers can use this to benchmark their Vimgolf-playing AI models.

No commits in the last 6 months. Available on PyPI.

Use this if you are developing or evaluating AI models that generate key sequences to complete Vimgolf challenges and need a reliable, customizable testing environment.

Not ideal if you are a human looking to play Vimgolf or learn Vim; this is a tool for automated AI evaluation, not interactive human use.

AI-testing algorithm-benchmarking text-editor-automation reinforcement-learning-environment Vim-scripting
Stale 6m
Maintenance 2 / 25
Adoption 5 / 25
Maturity 24 / 25
Community 0 / 25

How are scores calculated?

Stars

11

Forks

Language

Python

License

Unlicense

Last pushed

Sep 16, 2025

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/James4Ever0/vimgolf-gym"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.