Gamma-World: Multi-Agent World Model

A generative world model that simulates a shared environment for multiple independently controllable agents, scaling beyond two players.

Stars
★ 579
Last updated
5mo ago
License
Apache-2.0
Primary language
Python

At a glance

Works with
Portable with changes
You'll need
GPU hardwarePyTorchPythonShell / CLINetwork accessLocal filesystem
Typical use
Researchers studying multi-player game world models who need interactive simulated environments
Main limitation
Setup, inference, and training details live in docs/setup.md, docs/inference.md, and docs/training.md, which are not cached in the provided source, so exact commands cannot be confirmed
Website
research.nvidia.com ↗ set on GitHub
Maintenance
Commits in the last 6 monthslast commit 2026-06-17

What does this agent do, and when should you use it?

Gamma-World is an open-source generative multi-agent world model from NVIDIA research that rolls out a single shared environment in which multiple agents act simultaneously and remain independently controllable. It ingests synchronized observations and actions per agent, tokenizes each stream with shared visual and action encoders, and generates future multi-agent rollouts with a causal multi-agent DiT. Simplex Rotary Agent Encoding gives each agent a distinct rotary phase while keeping all agents permutation-equivalent, and Sparse Hub Attention routes cross-agent information through learnable hub tokens in linear time. A full-context diffusion teacher is distilled into a block-causal student that streams at 24 FPS with KV caching, and the encoding enables zero-shot generalization from two to four players.

The repository implements both inference and training for multi-agent video world modeling. It reads synchronized observations and actions from multiple agents, tokenizes each agent's stream with shared visual and action encoders, and runs a causal multi-agent DiT to produce future multi-agent rollouts. Inference supports bidirectional, causal, and causal-few-step models on user-supplied initial frames and actions, and the distillation stage converts the teacher into a causal student that generates temporal blocks sequentially with KV caches at 24 FPS. Training converts a released checkpoint to DCP and then runs the teacher, causal, and DMD stages.

  1. Researchers studying multi-player game world models who need interactive simulated environments
  2. Robotics labs exploring multi-robot coordination through shared world model rollouts
  3. Teams wanting to generalize from two-player training data to four-player scenes without retraining
  4. Engineers distilling a diffusion teacher into a real-time causal student
  5. Researchers benchmarking permutation-symmetric encodings and cross-agent attention designs

How do you install or deploy this agent?

Installation is documented in docs/setup.md, which is not included in the provided source, so exact commands cannot be given here. The runtime requires Python, PyTorch, and GPU hardware. Start by cloning the repository and then follow the setup document:

git clone https://github.com/nv-tlabs/Gamma-World.git
cd Gamma-World

Then run the environment and dependency installation described in docs/setup.md.

How do you use this agent?

Inference is documented in docs/inference.md and covers running the bidirectional, causal, and causal-few-step models on your own initial frames and actions. Training is documented in docs/training.md and covers converting a released checkpoint to DCP and training the teacher, causal, and DMD stages. Exact commands are not included in the provided source; consult these documents.

# View the inference and training documentation
cat docs/inference.md
cat docs/training.md

The project page provides videos and qualitative results for evaluating the model before running it.

What are this agent's strengths and limitations?

Pros
  • Simplex Rotary Agent Encoding is parameter-free and permutation-symmetric, removing learned per-slot identities and a fixed agent order
  • Sparse Hub Attention reduces cross-agent attention from O(N²) to O(N) and is shown to lower latency and FLOPs as agents increase
  • Distilled causal student enables real-time 24 FPS block-causal streaming with KV caching
  • Apache-2.0 license supports research and commercial use, and code plus training pipeline ship together
  • Demonstrates transfer from virtual game settings to real-world multi-robot coordination
Limitations
  • Setup, inference, and training details live in docs/setup.md, docs/inference.md, and docs/training.md, which are not cached in the provided source, so exact commands cannot be confirmed
  • Requires GPU hardware and heavy deep-learning dependencies; first run will not complete in minutes
  • New 2026 release with an unsettled community ecosystem and unclear checkpoint availability
  • No evidence of integration with chat platforms, API standards, or agent packaging conventions

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
Gamma-World: Multi-Agent World Model This agent 38 · Major gaps — ★ 579 5mo ago Python —
4KAgent 39 · Major gaps CLIFree + model costs ★ 842 1y ago Python —
Principia 66 · Some gaps CLIFree + model costs ★ 1.1k 1mo ago Rich Text Format —
AgileRL 62 · Some gaps Library / SDKFreemium ★ 970 today Python —

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
38/ 100 5-point scale 1.9 / 5
Trust 8/29
Reliability 6/14
Adaptability 8/18
Convention 9/18
Effectiveness 4/13
Verifiability 3/8
Why each dimension lost points
Trust8 / 29 · 1.4/5

This is a research world-model codebase, not an Agent product with permission boundaries. README and pyproject describe no permission model, confirmation flow, or data-flow disclosure; the only dependency is pinned cosmos-oss==0.1.0 via workspace override with no vulnerability audit or hash locking, so dependency_security is 1. Source files carry SPDX and Apache-2.0 headers, giving clear attribution (2). No rollback mechanism is evidenced (0).

Reliability6 / 14 · 2.1/5

The README's method claims (Simplex Rotary Agent Encoding, Sparse Hub Attention, 24 FPS) are internally consistent, and test files show backend skip conditions and tolerance assertions, indicating some engineering rigor (2). Dependency availability is gated on specific CUDA/GPU architectures (Hopper/Blackwell), unusable in ordinary environments, and no failure-message design is visible, each 1.

Adaptability8 / 18 · 2.2/5

README targets researchers with setup/inference/training doc entry points, a clear scenario (2); but capability boundaries (supported inputs, VRAM needs, non-GPU use) are unstated and trigger conditions vague, and environment fit is Linux+CUDA only, each 1.

Convention9 / 18 · 2.5/5

README is well-structured with a User Guide index (2); install notes only link docs/setup.md not included in the packet (1); package naming and structure are stable (2); examples are images/video only with no FAQ (1); known limitations are not listed (1); LICENSE is full Apache-2.0 and consistent with pyproject (3); no changelog/version history beyond two News items (1); maintenance responsibility is unclear with an unverified publisher (1).

Effectiveness4 / 13 · 1.5/5

As a research reproduction package, output usability depends on checkpoints and docs not provided (1); marginal value over single-agent world models exists but requires heavy compute (1); cost/benefit is unquantified (1).

Verifiability3 / 8 · 1.9/5

Paper and arXiv links are traceable, but no benchmark scripts in the packet map to the paper's claims (1); tests and README claims lack cross-corroboration (1); fact and inference are mostly separated but not explicitly labeled (1).

Risks and how to mitigate them
  • Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
  • Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
  • This is a research codebase, not a deployable Agent product; it lacks permission, confirmation, and data-flow controls and should not be assessed as an Agent framework for safety.
  • The cosmos-oss==0.1.0 dependency is workspace-overridden without hash locking or vulnerability audit, leaving supply-chain risk unknown.
  • Running requires Hopper/Blackwell-class GPUs and specific CUDA versions; ordinary environments cannot reproduce it.
  • Publisher identity is unverified by the FollowAgents registry; maintenance responsibility and update path are unclear.
  • Performance claims such as 24 FPS and four-player generalization have no in-packet benchmark scripts to verify them.
Evidence confidence: Low Reviewed Nov 17, 2026 Reviewed revision 6a95de85c439
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/gamma-world.svg)](https://followagents.com/en/agents/gamma-world)
<a href="https://followagents.com/en/agents/gamma-world"><img src="https://followagents.com/badge/gamma-world.svg" alt="FARS review"></a>

FAQ

Is Gamma-World: Multi-Agent World Model open source?
Yes. The source code is on GitHub (nv-tlabs/Gamma-World) under the Apache-2.0 licence.
Is Gamma-World: Multi-Agent World Model safe to use?
FollowAgents' FARS review (Nov 17, 2026) scored Gamma-World: Multi-Agent World Model 8/29 on trust and safety. The review did not find these safety controls in the source: confirmation before acting, rollback or recovery path. Before giving it real accounts or data: Turn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
Is Gamma-World: Multi-Agent World Model still maintained?
Development has slowed: the latest commit on GitHub is from 2026-06-17, within the last six months but not the last 30 days.
Who makes Gamma-World: Multi-Agent World Model?
Gamma-World: Multi-Agent World Model is published on GitHub by the account nv-tlabs. FollowAgents has not verified which person or company is behind that account.
What is Gamma-World: Multi-Agent World Model's official website?
The project's GitHub repository lists https://research.nvidia.com/labs/sil/projects/gamma-world/ as its website. That link is set by the repository owner; the source code itself is on GitHub (nv-tlabs/Gamma-World).
Was this page helpful?
View on GitHub ↗ Install ↓

Related concepts