Reflex-1
Decision models for agentsA 421M-parameter model for tool routing, intent classification and action selection. Public weights; runs on CPU or GPU.
Public weights
Independent research in machine intelligence
Intelligence
that can act.
We build intelligence that learns from experience and acts in the world.
Our workre1 / Spatial memoryResearch preview
Recorded in the re1 viewer. A completed scene, revisited in 3D.
Current work
Samsara-VLA
Robot learningRobot control with recurrent memory. 94.50% native LIBERO success in a 217M-parameter policy.
Experimental
Colony
Persistent agentsPersistent agents that work in your tools, remember your projects and build what you need.
Technical preview
re1
Spatial memoryPersistent video memory, scene reconstruction and simulation artifacts for physical-AI research.
Research preview
VIO-lens-2
ResearchResearch in progress.
In progress