Stars
The best-benchmarked open-source AI memory system. And it's free.
The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
Make your agents learn from experience. One protocol for weights, harness and routing.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
A toolkit for reproducible reinforcement learning research.
Minimal solvers for calibrated camera pose estimation
A GPU-accelerated TSDF and ESDF library for robots equipped with RGB-D cameras.
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Sourcetrail - free and open-source interactive source explorer
A toolbox for mapping and localization with line features.
A flexible, high-performance 3D simulator for Embodied AI research.
Repository for the code used in the Medium articles about Python libraries for 3D analysis, visualization and manipulation of point clouds and meshes
[ECCV 2024] MAP-ADAPT: Real-Time Quality-Adaptive Semantic 3D Maps
Holistically-Attracted Wireframe Parsing [TPAMI'23] & [CVPR' 20]
[CVPR'19] Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding
PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
A system for building 3D Scene Graphs from sensor data in real-time
A library for flexible voxel-based mapping, mainly focusing on truncated and Euclidean signed distance fields.
A flexible submap-based framework towards spatio-temporally consistent volumetric mapping and scene understanding.
Refine high-quality datasets and visual AI models
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions