# Sentdex/pygta5

Explorations of Using Python to play Grand Theft Auto 5.

Repository: https://github.com/Sentdex/pygta5
Canonical: https://ross.abutalabs.com/products/pygta5
Language: Python
License: MIT
License Family: permissive
Last push: 2023-03-08T07:06:53+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3437, "days_push": 1274, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3906, forks 803 (observed 2026-08-28T04:08:28.714312+00:00)

## What it is
A reboot of Sentdex's project using Python and deep learning to play Grand Theft Auto 5, featuring an AI driver called Charles trained via CNN regression models. It includes a distributed system of data collectors, NPCs, a central server, and a trainer that streams model training live.

## Use cases
- learn how to build an AI that plays GTA 5
- train a neural network to drive a car in a game
- collect training data automatically from game instances
- follow a deep learning game-playing tutorial series
- experiment with CNN models like Xception and InceptionResNetv2 for game control
- set up a distributed data collection and training pipeline for game AI

## When to choose
- you want to learn applied deep learning by making an AI play a game
- you want a reference architecture for automated game data collection and live training
- you enjoyed the original 2017 Python Plays GTA series and want the modern approach

## When to avoid
- you need a production-ready self-driving or game-bot framework
- you want a maintained library with stable APIs and releases
- you cannot run GTA 5 on Windows with a GPU

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, simulation, data-generation
- domain: reinforcement-learning, computer-vision, gaming-tools, artificial-intelligence, tutorials
- platform: python, windows
- tags: self-driving-agent, gta5, imitation-learning, sentdex, game-ai, educational, gpu

## Member repositories
- Sentdex/pygta5 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:28.714312+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:25:06.732490+00:00, confidence not recorded.
  - readme: https://github.com/Sentdex/pygta5 (fetched 2026-08-28T04:08:28.714312+00:00, sha dcae0fd4739a)
- Data as of 2026-08-30T08:39:29.467469+00:00.