facebookresearch/InteractiveWorld
Can I trust it?
Be careful with this one.
Warnings Check
Very new: it was created 11 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 7 days ago.
Licence Careful
No licence: legally you can't reuse the code, unless the README says otherwise.
Quick checks from public data. They help, but they are no guarantee.
What it is
A simulator where a human avatar in 44 BEHAVIOR-1K 3D scenes is driven by short action commands such as walking, grasping and putting objects, and returns first-person views. It also provides InteractiveBench, 120 frozen multi-turn tasks in which one model plays the assistant…
Who it's for
Researchers evaluating interactive MLLM assistants and wearable AI agents, with Isaac Sim and NVIDIA GPUs
How to use it
Install
pip install -r requirements.txtFrom its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up facebookresearch/InteractiveWorld in my project. Follow its README: https://github.com/facebookresearch/InteractiveWorld. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/facebookresearch/InteractiveWorld?ref=badge)Similar repos
- jwang771/3d-world-simulator
Research code for a hybrid particle-voxel model that learns dynamics for multimodal 3D world simulation of deformable and rigid objects. It trains a voxel autoencoder per task (cloth, box, pusht, plug
- QwenLM/BlenderWorld
Benchmark for evaluating visual agents on 3D creation tasks in Blender, built from real-world references such as text, images and video. Agents deliver an editable Blender project and exports, which a
- THUSI-Lab/GameScaling
Inference client and system-prompt template for GameScaling, a set of Qwen3.5 vision-language models with continued pre-training on keyboard-and-mouse gameplay. Given the current frame and recent hist
- StreamEval/StreamEval
A Python benchmark for evaluating interactive streaming video generation models across five tasks, including digital-human dialogue, avatar performance, world generation and video editing. Inputs arri
- clipspark/multiworldbench
Benchmark for evaluating independently controlled Minecraft views on navigation, shared-world interactions and revisit consistency. Includes V4 case suites (495 cases), metric implementations, scoring
- hey-cjj/LAW
Official implementation of the LAW paper, which combines VLM planning, state assessment and value estimation with FastWAM or OpenWAM world-action models. The repository provides training and inference