# open-gigaai/giga-world-policy

GigaWorld-Policy: An Efficient Action-Centered World–Action Model

Repository: https://github.com/open-gigaai/giga-world-policy
Canonical: https://ross.abutalabs.com/products/giga-world-policy
Language: Python
License Family: other
Last push: 2026-07-21T06:25:27+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 41, longevity 13
- inputs: {"age_days": 183, "days_push": 43, "days_rel": 183, "gap_med": null, "n_releases_24m": 1}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1398, forks 107 (observed 2026-08-28T04:04:36.861396+00:00)

## What it is
GigaWorld-Policy is a World Action Model (WAM) for robot policy learning that jointly models actions and future visual observations during training while using action-only decoding at inference. Its 0.5 release uses a Mixture-of-Transformers architecture to achieve 85ms inference latency on a local RTX 4090 for real-time closed-loop robot control.

## Use cases
- train robot policies with world models
- real-time robot control with low latency inference
- learn robot manipulation policies from visual demonstrations
- run a world action model locally on a single GPU
- research action-conditioned world modeling for robotics

## When to choose
- you need efficient real-time robot policy inference on consumer GPUs
- you want to leverage future visual dynamics as dense supervision for policy learning
- you are researching world models or action models for robot control

## When to avoid
- you need a general-purpose vision-language model rather than a robot control policy
- you lack GPU hardware for training or inference
- you need a plug-and-play robot stack without ML research involvement

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-training, simulation
- domain: robotics, machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: world-model, robot-policy-learning, action-model, mixture-of-transformers, real-time-inference, robotics, pytorch, gpu, linux

## Member repositories
- open-gigaai/giga-world-policy (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:36.861396+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 2026-08-30T04:39:13.849000+00:00, confidence not recorded.
  - readme: https://github.com/open-gigaai/giga-world-policy (fetched 2026-08-28T04:04:36.861396+00:00, sha 445fbcbb4877)
- Data as of 2026-08-30T08:39:29.467469+00:00.