# SerpentAI/SerpentAI

Game Agent Framework. Helping you create AIs / Bots that learn to play any game you own!

Repository: https://github.com/SerpentAI/SerpentAI
Canonical: https://ross.abutalabs.com/products/serpentai
Homepage: http://serpent.ai
Language: Python
License: MIT
License Family: permissive
Topics: python, video-games, artificial-intelligence, machine-learning, computer-vision, framework, deep-learning
Archived: true
Last push: 2022-11-07T01:59:31+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3426, "days_push": 1396, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6992, forks 799 (observed 2026-08-28T04:09:52.310497+00:00)

## What it is
Serpent.AI is a Python framework for building game agents—AIs and bots that learn to play any video game you own—turning games into machine learning sandbox environments. It is plugin-based for both game support and agents, with CLI tools and supporting modules for common game-agent scenarios.

## Use cases
- train an AI to play a video game
- build a bot that learns any game
- use games as reinforcement learning environments
- experiment with deep RL on game screenshots
- create portable game agent plugins
- do machine learning research with video games

## When to choose
- you want to apply deep reinforcement learning or computer vision to a game you own
- you need a plugin-based, extensible game agent framework in Python
- you want a fun hobbyist ML sandbox with CLI tooling

## When to avoid
- you need macOS support or a maintained, actively developed project
- you need production-grade game botting with anti-detection
- you want a framework with modern Python and up-to-date dependencies

## Facets
- artifact type: framework
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, reinforcement-learning, cli, plugin-system
- domain: artificial-intelligence, machine-learning, computer-vision, gaming-tools
- platform: python, windows, cross-platform
- tags: game-agents, reinforcement-learning, video-games, ai-bots, game-automation, game-development, linux

## Member repositories
- SerpentAI/SerpentAI (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:52.310497+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 2026-08-29T17:41:07.001691+00:00, confidence not recorded.
  - readme: https://github.com/SerpentAI/SerpentAI (fetched 2026-08-28T04:09:52.310497+00:00, sha d32f821acec0)
- Data as of 2026-08-30T08:39:29.467469+00:00.