# ivanseidel/IAMDinosaur

🦄 An Artificial Inteligence to teach Google's Dinosaur to jump cactus

Repository: https://github.com/ivanseidel/IAMDinosaur
Canonical: https://ross.abutalabs.com/products/iamdinosaur
Language: JavaScript
License: MIT
License Family: permissive
Topics: neural-network, genome, dino, genetic-algorithm, google-dinosaur, artificial-intelligence
Last push: 2018-02-07T09:02:56+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3902, "days_push": 3129, "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 2804, forks 533 (observed 2026-08-28T04:07:22.738562+00:00)

## What it is
A Node.js application that uses neural networks and a genetic algorithm to teach Google Chrome's offline dinosaur game to jump cacti autonomously. It reads game pixels from the screen via RobotJs and evolves a population of 12 genomes through selection, cross-over, and mutation.

## Use cases
- teach an AI to play the Chrome dinosaur game
- learn how genetic algorithms evolve neural networks
- demo of neuroevolution for a simple game
- experiment with fitness-based genome selection
- educational example of AI playing a browser game

## When to choose
- you want a hands-on, visual introduction to neuroevolution
- you need a small, readable codebase demonstrating genetic algorithms with neural networks
- you want an educational demo linking screen input to an AI agent

## When to avoid
- you need a production-grade reinforcement learning framework
- you want headless automation without screen capture
- you need a maintained or actively developed project (last release 2018)
- you require cross-platform guarantees, since RobotJs can be difficult to build

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, simulation, workflow-automation
- domain: artificial-intelligence, machine-learning, gaming-tools, education
- platform: windows
- tags: neural-network, genetic-algorithm, reinforcement-learning, chrome-dinosaur, synaptic, robotjs, screen-scraping, nodejs, macos, linux, desktop

## Member repositories
- ivanseidel/IAMDinosaur (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:22.738562+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 2026-08-30T08:14:30.459225+00:00, confidence not recorded.
  - readme: https://github.com/ivanseidel/IAMDinosaur (fetched 2026-08-28T04:07:22.738562+00:00, sha 447e9fdc6a99)
- Data as of 2026-08-30T08:39:29.467469+00:00.