The AI Stack
Sign in

Lightmatter

Develops photonic chips and interconnects for efficient AI computing.

Updated April 2026

Overview

Founded
2017
Headquarters
Mountain View, CA
Segment
Optical Interconnect & Photonics

Product overview

Lightmatter builds photonic computing hardware that uses light instead of electrons for data processing and communication to boost AI performance and cut energy use in data centers. Key products include Passage, a photonic interconnect for scaling AI supercomputers with high bandwidth and low power, and Envise, the first general-purpose photonic AI accelerator for neural networks. The company, founded by MIT alumni, targets bottlenecks in AI training and inference for massive GPU clusters.

Revenue model

Sells photonic chips, interconnects, and AI accelerators to hyperscalers and data centers

Moat

  • Proprietary Technology
  • Patents/IP
  • Scale Advantages

Lightmatter's key competitive moat is its proprietary photonic computing technology, including chips like Envise and interconnects like Passage, which use light instead of electrons for superior speed, energy efficiency, and bandwidth in AI and high-performance computing, addressing silicon limitations.

Headwinds

Photonic computing adoption requires fundamental changes to existing AI hardware ecosystems and software stacks.