Get the weekly radar
One short email with the freshest products, every week.
Grounded in available product and source data
Eximius Labs builds open-weight multimodal models that run on your own hardware: the embedding, perception, and memory layers for physical AI. The technical report is on arXiv: https://arxiv.org/abs/2607.18666. Try a real robot's memory in the live playground: https://www.eximiuslabs.com/playground.
We freeze a strong base model and add new senses from the outside, so existing embeddings stay valid and gaining a modality never forces a re-index. One shared vector space spans text, image, video, audio, thermal, and motion (IMU).
One vector space for cross-modal retrieval, RAG, clustering, and semantic search.
Dense scene understanding and geometric place recognition on a frozen vision backbone, projected into the Fusion Embedding space. Code: https://github.com/Eximius-Labs/fusion-perception.
The open cross-modal memory layer for physical AI, built on Fusion Embedding. It indexes a robot's video, audio, and motion into one embedding space on a shared clock and answers questions about it in plain language, including temporal reasoning that retrieval alone cannot do.
Code: https://github.com/Eximius-Labs/engram · PyPI: https://pypi.org/project/engram-robomem · Playground: https://www.eximiuslabs.com/playground
Everything is open weight and self-hostable. Core models are research preview; the sensor packs are CC-BY-NC-4.0.
