Home Projects habitat-lab
habitat-lab
Python

habitat-lab

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

by facebookresearch · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
aicomputer-visiondeep-learningMITPython
View on GitHub
In plain words

Habitat simulates indoor environments at thousands of frames per second so agents can learn navigation and object manipulation from vision.

From the README

Install
git clone --branch stable https://github.com/facebookresearch/habitat-lab.git
      cd habitat-lab
      pip install -e habitat-lab  # install habitat_lab

Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
habitat-lab — GitHub preview card
📈 Star history
3.1k3.0k
2026-07-072026-08-31
📈 Track habitat-lab

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

habitat-lab has 3.1k stars on GitHub. It has been forked 686 times. habitat-lab is written mainly in Python. It has been in active development since 2019. habitat-lab is available under the MIT license. Its main topics are ai, computer-vision, deep-learning, deep-reinforcement-learning.

Read the full guide
Frequently asked questions

What is habitat-lab?

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Is habitat-lab open source?

habitat-lab is an open-source project. It is released under the MIT license.

Is habitat-lab free?

Yes. habitat-lab is free and open source — you can use, modify and self-host it.

What license does habitat-lab use?

habitat-lab is available under the MIT license.

What language is habitat-lab written in?

habitat-lab is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — habitat-lab

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=facebookresearch-habitat-lab)](https://olud.ai/project/facebookresearch-habitat-lab.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
SMARTS
Scalable Multi-Agent RL Training School for Autonomous Driving
1.1k · autonomous-driving
sharessimulatorreinforcement-learning
SimWorld
SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds
732 · agent
sharessimulatorrobotics
BFM-Zero
BFM_Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Rein…
682 · humanoid
sharessim2realreinforcement-learning
hands-on-rl
Free course that takes you from zero to Reinforcement Learning PRO 🦸🏻‍🦸🏽
1.6k · deep-reinforcement-learning
sharesdeep-reinforcement-learningreinforcement-learning
drl-zh
Deep Reinforcement Learning: Zero to Hero!
2.3k · deep-learning
sharesdeep-reinforcement-learningreinforcement-learning
reward-learning-rl
[RSS 2019] End-to-End Robotic Reinforcement Learning without Reward Engineering
374 · deep-learning
sharesdeep-reinforcement-learningreinforcement-learning
FlashSAC
FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control
334 · reinforcement-learning
sharesroboticsreinforcement-learning
MARL-Algorithms
Implementations of IQL, QMIX, VDN, COMA, QTRAN, MAVEN, CommNet, DyMA-CL, and G2ANet on SMAC, t…
1.8k · deep-reinforcement-learning
sharesdeep-reinforcement-learningreinforcement-learning
DexterousHands
This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym
1.1k · deep-reinforcement-learning
sharesdeep-reinforcement-learningreinforcement-learning
gps
Guided Policy Search
600 · deep-learning
sharesdeep-reinforcement-learningreinforcement-learning

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.