{"data":{"slug":"umass-embodied-agi-3d-mem","name":"3D-Mem","tagline":"3D scene memory for embodied AI exploration and reasoning","github_url":"https://github.com/UMass-Embodied-AGI/3D-Mem","owner":"UMass-Embodied-AGI","repo":"3D-Mem","owner_avatar_url":"https://avatars.githubusercontent.com/u/126135718?v=4","primary_language":"Python","stars":277,"forks":19,"topics":["ai","computer-vision","embodied-ai","spatial-intelligence"],"archived":false,"github_pushed_at":"2025-10-02T18:37:32+00:00","maintenance_label":"Slowing","stars_delta_30d":7,"url":"https://www.graphcanon.com/tools/umass-embodied-agi-3d-mem","markdown_url":"https://www.graphcanon.com/tools/umass-embodied-agi-3d-mem.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/umass-embodied-agi-3d-mem","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=umass-embodied-agi-3d-mem","description":"[CVPR 2025] Source codes for the paper \"3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning\"","homepage_url":"https://umass-embodied-agi.github.io/3D-Mem/","license":"MIT","open_issues":3,"watchers":9,"ai_summary":"A repository that provides source codes for implementing 3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning; focuses on generating and utilizing spatial intelligence in scenes to enhance embodied AI systems.","readme_excerpt":"## Installation\nSet up the conda environment (Linux, Python 3.9):\n```bash\nconda create -n 3dmem python=3.9 -y && conda activate 3dmem\n\npip install torch==2.0.1 torchvision==0.15.2 --index-url https://download.pytorch.org/whl/cu118\nconda install -c conda-forge -c aihabitat habitat-sim=0.2.5 headless faiss-cpu=1.7.4 -y\nconda install https://anaconda.org/pytorch3d/pytorch3d/0.7.4/download/linux-64/pytorch3d-0.7.4-py39_cu118_pyt201.tar.bz2 -y\n\npip install omegaconf==2.3.0 open-clip-torch==2.26.1 ultralytics==8.2.31 supervision==0.21.0 opencv-python-headless==4.10.* \\\n scikit-learn==1.4 scikit-image==0.22 open3d==0.18.0 hipart==1.0.4 openai==1.35.3 httpx==0.27.2                                                      \n\n```","github_created_at":"2024-12-09T21:16:07+00:00","created_at":"2026-07-11T12:32:00.897681+00:00","updated_at":"2026-09-25T06:00:20.122246+00:00","categories":[{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"embodied-ai","name":"embodied-ai"},{"slug":"spatial-intelligence","name":"spatial-intelligence"}],"trust":{"provenance":{"is_fork":false,"github_id":900996892,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-25T06:00:19.240Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":357,"last_release_at":null,"stars_delta_30d":7,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:32:16.335Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-25T06:00:19.760Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-25T06:00:19.760Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-25T06:00:19.760Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Use if your project involves embodied AI systems that require detailed scene understanding in 3D","Choose this tool when working with tasks like navigation or object manipulation based on 3D scene comprehension"],"when_not_to_use":["Avoid for environments where 2D image analysis suffices over deeper 3D spatial reasoning","This may not be suitable if real-time performance is more critical than the richness of 3D scene intelligence"],"source":"enrich:decision_facts","observed_at":"2026-07-16T22:16:29.442Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"3D-Mem excels in environments where embodied AI needs spatial intelligence for exploration and reasoning in 3D scenes."}]}}