{"data":{"slug":"facebookresearch-habitat-lab","name":"habitat-lab","tagline":"A modular high-level library to train embodied AI agents across a variety of tasks and environments.","github_url":"https://github.com/facebookresearch/habitat-lab","owner":"facebookresearch","repo":"habitat-lab","owner_avatar_url":"https://avatars.githubusercontent.com/u/16943930?v=4","primary_language":"Python","stars":3053,"forks":680,"topics":["ai","computer-vision","deep-learning","deep-reinforcement-learning","python","reinforcement-learning","research","robotics","sim2real","simulator"],"archived":false,"github_pushed_at":"2026-05-07T22:03:51+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/facebookresearch-habitat-lab","markdown_url":"https://www.graphcanon.com/tools/facebookresearch-habitat-lab.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/facebookresearch-habitat-lab","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=facebookresearch-habitat-lab","description":"A modular high-level library to train embodied AI agents across a variety of tasks and environments.","homepage_url":"https://aihabitat.org/","license":"MIT","open_issues":388,"watchers":43,"ai_summary":null,"readme_excerpt":"## Installation\n\n1. **Preparing conda env**\n\n   Assuming you have [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/install/) installed, let's prepare a conda env:\n   ```bash\n   # We require python>=3.9 and cmake>=3.14\n   conda create -n habitat python=3.9 cmake=3.14.0\n   conda activate habitat\n   ```\n\n1. **conda install habitat-sim**\n   - To install habitat-sim with bullet physics\n      ```\n      conda install habitat-sim withbullet -c conda-forge -c aihabitat\n      ```\n      Note, for newer features added after the most recent release, you may need to install `aihabitat-nightly`. See Habitat-Sim's [installation instructions](https://github.com/facebookresearch/habitat-sim#installation) for more details.\n\n1. **pip install habitat-lab stable version**.\n\n      ```bash\n      git clone --branch stable https://github.com/facebookresearch/habitat-lab.git\n      cd habitat-lab\n      pip install -e habitat-lab  # install habitat_lab\n      ```\n1. **Install habitat-baselines**.\n\n    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:\n\n      ```bash\n      pip install -e habitat-baselines  # install habitat_baselines\n      ```\n\n---\n\n## Docker Setup\nWe provide docker containers for Habitat, updated approximately once per year for the [Habitat Challenge](https://github.com/facebookresearch/habitat-challenge). This works on machines with an NVIDIA GPU and requires users to install [nvidia-docker](https://github.com/NVIDIA/nvidia-docker). To setup the habitat stack using docker follow the below steps:\n\n1. Pull the habitat docker image: `docker pull fairembodied/habitat-challenge:testing_2022_habitat_base_docker`\n\n1. Start an interactive bash session inside the habitat docker: `docker run --runtime=nvidia -it fairembodied/habitat-challenge:testing_2022_habitat_base_docker`\n\n1. Activate the habitat conda environment: `conda init; source ~/.bashrc; source activate habitat`\n\n1. Run the testing scripts as above: `cd habitat-lab; python examples/example.py`. This should print out an output like:\n    ```bash\n    Agent acting inside environment.\n    Episode finished after 200 steps.\n    ```\n\n---\n\n## License\nHabitat-Lab is MIT licensed. See the [LICENSE file](/LICENSE) for details.\n\nCopyright (c) Meta Platforms, Inc. and affiliates.\n\nThe trained models and the task datasets are considered data derived from the correspondent scene datasets.\n\n- Matterport3D based task datasets and trained models are distributed with [Matterport3D Terms of Use](http://kaldir.vc.in.tum.de/matterport/MP_TOS.pdf) and under [CC BY-NC-SA 3.0 US license](https://creativecommons.org/licenses/by-nc-sa/3.0/us/).\n- Gibson based task datasets, the code for generating such datasets, and trained models are distributed with [Gibson Terms of Use](https://storage.googleapis.com/gibson_material/Agreement%20GDS%2006-04-18.pdf) and under [CC BY-NC-SA 3.0 US license](https://creativecommons.org/licenses/by-nc-sa/3.0/us/).","github_created_at":"2019-02-04T23:12:51+00:00","created_at":"2026-07-11T12:23:09.407489+00:00","updated_at":"2026-07-11T12:23:14.270637+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"research","name":"research"},{"slug":"reinforcement-learning","name":"reinforcement-learning"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"ai","name":"ai"},{"slug":"python","name":"python"},{"slug":"robotics","name":"robotics"},{"slug":"deep-reinforcement-learning","name":"deep-reinforcement-learning"},{"slug":"computer-vision","name":"computer-vision"}],"trust":{"provenance":{"is_fork":false,"github_id":169164391,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T12:23:10.114Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":1,"days_since_push":64,"last_release_at":"2026-05-07T20:22:56Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:23:11.303Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T12:23:10.914Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-07-11T12:23:10.914Z","managed_saas":false},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-11T12:23:10.914Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-07-11T12:23:10.914Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-11T12:23:10.914Z"}}}}