facebookresearch/habitat-lab

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

77
/ 100
Verified

Supports diverse task types including navigation, rearrangement, instruction following, and human-in-the-loop interaction, with configurable embodied agents (robots, humanoids) and their sensor suites. Built on Habitat-Sim for physics simulation, it provides training pipelines for single and multi-agent reinforcement/imitation learning plus SensePlanAct evaluation frameworks with standardized benchmarking metrics across task domains.

2,876 stars and 1,403 monthly downloads. Available on PyPI.

Maintenance 10 / 25
Adoption 17 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

2,876

Forks

641

Language

Python

License

MIT

Last pushed

Feb 21, 2026

Monthly downloads

1,403

Commits (30d)

0

Dependencies

13

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/facebookresearch/habitat-lab"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.