PRIOR: Perceptual Reasoning and Interaction Research

High-impact open-source AI research

Featured Project

MolmoWeb

MolmoWeb is an open source web-browsing agent that can navigate and complete tasks in a browser on your behalf. Built on Molmo 2 in 4B and 8B sizes, it sets a new open-weight state of the art across four major web-agent benchmarks.

Embodied AI

Project Image

MolmoSpaces

MolmoSpaces is an open, simulator-agnostic ecosystem of richly annotated indoor environments enabling large-scale, diverse benchmarking of robot policies with sim-to-real transfer.

Learn More
MolmoAct

MolmoAct

MolmoAct is an open action reasoning model that thinks in 3D space, planning robotic manipulation tasks by grounding language instructions into spatial waypoints across diverse embodiments.

Learn More

Vision-Language

Molmo 2

Molmo 2

Molmo 2 is a family of state-of-the-art open video-language models built on the Molmo architecture, with leading performance in video understanding, temporal reasoning, and multimodal interaction.

Learn More
Project Image

Molmo

Molmo is a family of open state-of-the-art multimodal AI models that can understand images and point to what they perceive, enabling rich interactions with physical and virtual worlds.

Learn More

Earth Systems

Project Image

OlmoEarth

OlmoEarth is a spatio-temporal, multimodal foundation model for Earth observation, achieving state-of-the-art performance and powering an end-to-end platform for non-profits and NGOs.

Learn More
Project Image

Satlas

Satlas is an AI-powered platform that provides quarterly global updates on marine infrastructure, renewable energy sites, and tree cover using satellite imagery.

Learn More