StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

[ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning

[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

The open source coding agent.

Official implement of VGGT-Long

DUSt3R: Geometric 3D Vision Made Easy

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

ViPE: Video Pose Engine for Geometric 3D Perception

COLMAP - Structure-from-Motion and Multi-View Stereo

Community plugins list, theme list, and releases of Obsidian.

Grounding Image Matching in 3D with MASt3R

C++ implementation of Lie Groups using Eigen.

Claude Desktop for Debian-based Linux distributions

A LiDAR SLAM system that just works

ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language queries. ROSA helps robot developers inspect, diagnose, understand, and operate robots.

Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM software. Supports high-resolution formats and images with rotations. Both CLI and GUI are supported.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…