GraphCanon updated 3w · GitHub synced 3w
Decision brief
Habitat-Lab is a Python library for training embodied AI agents in virtual environments through deep and reinforcement learning techniques.
Good fit when
- Use Habitat-Lab when your project requires the simulation of complex environments for embodied AI tasks, such as navigation and interaction with objects
- If you are working on research projects involving robotics and computer vision where simulation is critical to test and validate your algorithms before physical trials, choose Habitat-Lab
Avoid when
- Avoid Habitat-Lab if the computational resources required for running the simulations exceed what is available or feasible in terms of cost
- Do not use Habitat-Lab when the project is solely focused on real-world data and does not necessitate virtual training environments, as setting up such a library might add unnecessary complexity
- Requirements:
- Min 8 GB RAM; Requires Docker; Python >=3.9 is required along with cmake>=3.14 for installation; For users working on machines equipped with NVIDIA GPUs, nvidia-docker installation is necessary to run the provided Docker containers
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (84d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install habitat-labSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Habitat-Lab provides tools for training AI in virtual environments using deep learning and reinforcement learning techniques, targeting tasks related to robotics and computer vision.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Jul 31, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Jul 31, 2026
- Languages
- python
Source: github.language+pyproject.toml · Jul 31, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 31, 2026)
# We require python>=3.9 and cmake>=3.14Source link
Tags
README
Installation
-
Preparing conda env
Assuming you have conda installed, let's prepare a conda env:
# We require python>=3.9 and cmake>=3.14 conda create -n habitat python=3.9 cmake=3.14.0 conda activate habitat -
conda install habitat-sim
- To install habitat-sim with bullet physics
Note, for newer features added after the most recent release, you may need to installconda install habitat-sim withbullet -c conda-forge -c aihabitataihabitat-nightly. See Habitat-Sim's installation instructions for more details.
- To install habitat-sim with bullet physics
-
pip install habitat-lab stable version.
git clone --branch stable https://github.com/facebookresearch/habitat-lab.git cd habitat-lab pip install -e habitat-lab # install habitat_lab -
Install habitat-baselines.
The command above will install only core of Habitat-Lab. To include habitat_baselines along with all additional requirements, use the command below after installing habitat-lab:
pip install -e habitat-baselines # install habitat_baselines
Docker Setup
We provide docker containers for Habitat, updated approximately once per year for the Habitat Challenge. This works on machines with an NVIDIA GPU and requires users to install nvidia-docker. To setup the habitat stack using docker follow the below steps:
-
Pull the habitat docker image:
docker pull fairembodied/habitat-challenge:testing_2022_habitat_base_docker -
Start an interactive bash session inside the habitat docker:
docker run --runtime=nvidia -it fairembodied/habitat-challenge:testing_2022_habitat_base_docker -
Activate the habitat conda environment:
conda init; source ~/.bashrc; source activate habitat -
Run the testing scripts as above:
cd habitat-lab; python examples/example.py. This should print out an output like:Agent acting inside environment. Episode finished after 200 steps.
License
Habitat-Lab is MIT licensed. See the LICENSE file for details.
Copyright (c) Meta Platforms, Inc. and affiliates.
The trained models and the task datasets are considered data derived from the correspondent scene datasets.
- Matterport3D based task datasets and trained models are distributed with Matterport3D Terms of Use and under CC BY-NC-SA 3.0 US license.
- Gibson based task datasets, the code for generating such datasets, and trained models are distributed with Gibson Terms of Use and under CC BY-NC-SA 3.0 US license.
For agents
This page has a .md twin and JSON over the API.