Alternatives to Mrpt

Open-source autonomous driving simulator for research and development.

Open-source street-view generation with precise 3D geometry control for AV research

Open-source scientific image processing for research and analysis

Open benchmarks and fusion pipeline for V2V cooperative perception in autonomous driving research.

Open-source Unreal Engine plugin for synthetic data generation and computer vision research.

Open-source benchmark for long-horizon, language-conditioned robot manipulation research.

Open source dev kit for AI-native robotics with leader-follower teleoperation.

Open-source data annotation platform for vision AI teams

Unified open-source multimodal AI for image understanding and generation, free to run or hosted.

Modular LiDAR SLAM framework for ROS 2 — free for research, Pro for products

Build, code, and play with open-source robot dog and cat kits for STEM learning

Open-source, real-time image and video object segmentation with promptable control from Meta AI.

Open-source procedural generator for infinite photorealistic 3D worlds and synthetic data

Open-source diffusion framework for instruction-following computer vision.

An open-source MLLM-powered universal task router that delegates 20+ computer vision tasks to specialist models.

Open-source Python SDK for training and deploying physical AI on robots.

AI-powered robotics that automate wet lab science experiments, turning prompts into executed protocols.

AI facial analysis that turns 160+ beauty markers into a personalized, non-surgical glow-up plan.

Omni-bodied robotic intelligence: one AI brain to control any robot for any physical task

Alphabet X's per-plant AI crop intelligence, now powering Driscoll's and John Deere

General-purpose robot foundation models with FutureVision control for heavy-duty industrial automation.

General-purpose AI foundation models that control any robot, any task.

License proven L4 autonomous driving technology for all roads and rides.

Mapless embodied AI driving software for any vehicle, anywhere.

Offline, AI-assisted image annotation with SAM2, SAM3 & YOLO-World — one-time purchase, no subscription.

Semantic video search with timestamped evidence for AI agents and local libraries.

Auto-label images and train custom vision models with zero manual annotation.

Tactile capture hardware that records touch-aware demonstrations for dexterous robot training.

Real-world egocentric video and robot data for embodied AI training.

Turn satellite imagery into explorable 3D urban scenes with diffusion refinement