BrainChip Launches AI Development Kit for Raspberry Pi
The AKD1500-based kit enables low-power, on-chip learning to accelerate the development of always-on edge AI applications.
Updated on Oct. 29, 2026 in Semiconductors
Live Poll
Do you trust that keeping artificial intelligence processing on local devices improves your personal data privacy?
BrainChip has launched a new development kit for the Raspberry Pi 5 that integrates the AKD1500 neuromorphic M.2 board. This kit is now available for purchase and allows for on-chip learning, keeping data processing local to the device.
Why it matters
The development kit offers engineers a low-power method to evaluate always-on artificial intelligence applications on standard hardware. By utilizing the same processor for both prototyping and production, it streamlines the path for deploying edge computing models.
The global edge computing market is projected to reach $317.39 billion by 2031, up from $111.34 billion in 2026. The technical performance of this specific kit relative to prior generations remains unbenchmarked by third parties.
The players
BrainChip
A developer of event-based neuromorphic AI processors and edge computing software solutions.
The details
The AKD1500 processor uses event-based neuromorphic architecture to process only meaningful data spikes, which minimizes energy use. The kit interfaces with the Raspberry Pi 5 via PCIe and SPI, and BrainChip provides MetaTF software tools at no charge for building models. This setup enables on-chip learning, meaning the system can recognize new object classes without needing to send data back to the cloud for retraining.
Timeline
October 29, 2026: BrainChip launched the AKD1500 Raspberry Pi 5 Development Kit.
2031: Projected end date for the current edge computing market growth forecast.
The Tech Race
This kit positions BrainChip to capture demand within the edge computing market, which is expected to grow to $317.39 billion by 2031. It directly targets developers seeking to implement always-on AI by leveraging familiar hardware platforms.
Engineers and developers can purchase the kit now through the BrainChip shop to begin prototyping edge AI applications. The platform supports standard container workflows via preloaded Docker images for benchmarking performance.
The takeaway
The move toward local, on-chip learning significantly reduces reliance on cloud connectivity for always-on AI tasks. Watch for future benchmarks demonstrating power efficiency gains when moving from this Raspberry Pi-based prototype to a finalized production-ready module.
Further reading
For more on the hardware enabling on-device processing, see our Semiconductors section.
Source note: This article includes information reported by The Manila times.
Live Poll
Do you trust that keeping artificial intelligence processing on local devices improves your personal data privacy?
