Innatera Launches Synfire, an Open Platform for Neuromorphic Computing

The new community-driven platform aims to unify and accelerate the neuromorphic ecosystem by addressing fragmentation across tools, models, and deployment pipelines.

Apr. 7, 2026 at 8:35pm

Got story updates? Submit your updates here. ›

A highly detailed, glowing 3D macro illustration of a complex neuromorphic computing circuit board, with intricate patterns of illuminated neon cyan and magenta lines representing the flow of spiking neural network data, conveying a sense of advanced, futuristic technology powering the next generation of intelligent systems.Synfire, a new open platform, aims to unify the fragmented neuromorphic computing ecosystem and accelerate the deployment of advanced spiking neural network models.San Diego Today

Innatera has announced the launch of Synfire, an open, community-driven platform designed to standardize and scale neuromorphic systems. Synfire provides a centralized repository for neuromorphic models and full processing pipelines, enabling developers to publish, discover, and deploy spiking neural network (SNN) solutions with reduced friction.

Why it matters

Progress in neuromorphic computing has been hindered by a lack of interoperability, reproducibility, and standardized model exchange. Synfire addresses these challenges by offering a shared foundation for the neuromorphic community, helping to drive convergence and accelerate real-world deployment of neuromorphic AI solutions across industries.

The details

Synfire introduces a new platform for the neuromorphic community, including an open model registry for publishing and discovering SNN-based solutions, hardware-aware metadata to match models with validated execution targets, and an extensible architecture aligned with evolving standards such as the Neuromorphic Intermediate Representation (NIR). The platform is designed as a vendor-neutral open infrastructure, co-steered with broader industry and research communities.

  • Synfire was introduced at the Edge AI San Diego 2026 conference.
  • The platform will be fully available in late April 2026.

The players

Innatera

An open, community-driven platform that brings researchers, developers, and industry together to standardize and scale neuromorphic systems.

Steve Furber

Professor Emeritus of Computer Engineering at the University of Manchester, who believes Synfire will accelerate the transition of neuromorphic networks from usable to useful by offering developers the opportunity to lead innovation in this space.

Jens Egholm

Lead Author for Neuromorphic Intermediate Representation and Neuromorphic Computing Researcher, who notes that Synfire builds a shared language and commons for the neuromorphic community to upload, run, reproduce, and build on each other's work.

Petruț Antoniu Bogdan

Neuromorphic Architect at Innatera, who explains that Synfire introduces structure to standardize how models are shared, while remaining flexible enough to evolve with the field, in order to build a coherent ecosystem for efficient deployment of neuromorphic devices.

Got photos? Submit your photos here. ›

What they’re saying

“Progress for neuromorphic networks follows a clear path. First, we make them usable by building the infrastructure, tools, and shared foundations that allow people to work with them. Then, we make them useful, enabling them to solve real problems, adapt to real environments, and deliver real impact.”

— Steve Furber, Professor Emeritus of Computer Engineering at the University of Manchester

“Synfire is how neuromorphic computing gets out of the lab. Current AI hardware was not built for real-world intelligence. Neuromorphic systems are, but only if models, benchmarks, and hardware can speak the same language.”

— Jens Egholm, Lead Author for Neuromorphic Intermediate Representation and Neuromorphic Computing Researcher

“We have made incredible progress in neuromorphic hardware and model design, but the surrounding ecosystem is still fragmented. There is no consistent way to capture how a model was built, how it should run, or where it has been validated. That makes reuse difficult and slows down real deployment. Synfire introduces structure to fill these gaps by standardizing how models are shared, while remaining flexible enough to evolve with the field.”

— Petruț Antoniu Bogdan, Neuromorphic Architect at Innatera

What’s next

Synfire is now open for registration and will be fully available in late April 2026, providing developers with a centralized platform to publish, discover, and deploy spiking neural network solutions.

The takeaway

Synfire represents a significant step forward in unifying the fragmented neuromorphic computing ecosystem, enabling faster innovation and real-world deployment of neuromorphic AI across industries by providing a shared foundation for model sharing, hardware integration, and reproducible workflows.