allenai/ai2thor
An open-source platform for Visual AI.
This platform helps researchers test and train embodied AI agents in near photo-realistic virtual environments. It takes in various agent types and actions, simulating their interactions with diverse scenes and objects. The output includes different image modalities (like RGB, depth, semantic segmentation) and detailed metadata about the environment state. It's designed for AI/robotics researchers and engineers working on tasks like common sense reasoning, object manipulation, and sim-to-real transfer.
1,679 stars.
Use this if you need to simulate complex agent-environment interactions in highly detailed, customizable virtual settings for AI research and development.
Not ideal if you are looking for a simple data augmentation tool or a lightweight visualization library without agent interaction capabilities.
Stars
1,679
Forks
278
Language
C#
License
Apache-2.0
Category
Last pushed
Nov 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/allenai/ai2thor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
VIAME/VIAME
Video and Image Analytics for Multiple Environments
aimh-lab/visione
An AI-powered interactive video retrieval system
instill-ai/console
📺 Instill Console for 🔮 Instill Core: https://github.com/instill-ai/instill-core
wellflat/imageprocessing-labs
computer vision, image processing and machine learning on the web browser or node.
ZackAkil/video-intelligence-api-visualiser
A simple app that lets you visualise annotations from the Google Cloud Video Intelligence API...