NEURA and NXAI are building working and episodic memory for robots
NEURA Robotics and NXAI plan to combine Neuron AI with the xLSTM architecture so cognitive robots can track state across long tasks and draw on prior experience.
AT A GLANCE
Key points
- The partners will combine NEURA’s Physical AI stack with NXAI’s xLSTM architecture
- Working memory tracks immediate task state across many steps
- Episodic memory is intended to draw on prior process experience
- The NXAI model is planned as a second option on Neuraverse
What is changing?
NEURA Robotics and NXAI announced on October 20 that they will jointly develop a memory component for cognitive robots. The work will build on Neuron AI, which combines 3D vision, touch, audio, robot state, and language in one model, while integrating NEURA’s Physical AI stack with NXAI’s xLSTM architecture for updating state across long sequences.
The partnership focuses on two memory levels. Working memory would preserve immediate task state, such as whether a component has been inserted or a door is open. Episodic memory is intended to let a robot draw on earlier experience during repeated processes.
NXAI’s xLSTM-based model is planned as a second option alongside Neuron AI on Neuraverse. Companies would be able to fine-tune it for their tasks, test it in NEURA Gyms, and deploy it on suitable robots. The announcement describes a planned integration, not a completed product.
Explore the original sources
Source date: 20 October 2026.
Published by AI Radar: 20 Oct 2026, 11:12 (Istanbul, UTC+3).
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.
Loading comments…