# amap-cvlab/ABot-World

Infinite Interactive World Rollout on a Single Desktop GPU

Repository: https://github.com/amap-cvlab/ABot-World
Canonical: https://ross.abutalabs.com/products/abot-world
Homepage: https://abot-world.amap.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: worldmodel
Last push: 2026-08-21T12:25:45+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 9
- inputs: {"age_days": 139, "days_push": 12, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2462, forks 122 (observed 2026-08-28T04:06:53.670785+00:00)

## What it is
ABot-World is an open-source interactive world model that generates infinite, explorable video worlds from a single image, running on a single desktop GPU. It powers ABot World Studio, a web service that turns uploaded photos into navigable, extendable interactive video spaces.

## Use cases
- generate an explorable interactive world from a single photo
- run a world model rollout on a consumer desktop GPU
- create infinite interactive video environments from images
- build text-to-world or image-to-world generation pipelines
- explore AI-generated roaming worlds in a browser

## When to choose
- you need an interactive video world model that runs on a single desktop GPU
- you want to turn images into navigable, extendable video spaces
- you are researching world models or interactive video generation

## When to avoid
- you need a general-purpose video generation model for standard video synthesis
- you have no GPU available
- you need a production 3D engine rather than a neural world model

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, video-processing, llm-inference
- domain: artificial-intelligence, machine-learning, simulation
- platform: python
- tags: world-model, interactive-world-generation, video-generation, single-gpu, image-to-world, video, gpu, linux

## Member repositories
- amap-cvlab/ABot-World (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:53.670785+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 2026-08-30T02:29:17.830565+00:00, confidence not recorded.
  - readme: https://github.com/amap-cvlab/ABot-World (fetched 2026-08-28T04:06:53.670785+00:00, sha 558db7c89577)
  - homepage: https://abot-world.amap.com (fetched 2026-08-29T10:11:17.102408+00:00, sha 770a4202b3b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.