High-end AI and simulation workstation powered by AMD Threadripper 7000 series CPUs and up to 3x AMD Instinct MI210 GPUs, with optional FPGA acceleration via Kalray TC4 DPU accelerator or AMD/Xilinx Alveo UL3524. Ideal for LLM fine-tuning, agentic AI, and multi-accelerator workloads on your desk.

Flexible desktop system built around Intel Core i9 + NVIDIA RTX 4060/4070+ Kalray TC4 acceleration, with options for NVIDIA RTX5000/6000 or AMD Alveo U50 FPGA. Targets researchers and developers needing a balance between cost, power consumption, and modular heterogeneous compute.

Small-form-factor version of the Cyber Core, integrating a single accelerator (FPGA or MPPA). Ideal for mobile or edge-focused teams needing compact multi-architecture performance.

Modular edge board combining Kalray Coolidge MPPA, Xilinx Versal AI FPGA, and AMD CPU. Built for real-time video, robotics, and agentic inference in power-constrained or embedded environments.

Carrier-grade board for testing and deploying Kalray MPPA in PCIe-connected environments. Includes onboard JTAG, management, CAN bus, and supports direct integration into HPC or industrial systems.

Developer-friendly Kalray platform based on Coolidge MPPA. Offers full SDK access and debugging capabilities — ideal for software bring-up, bare-metal experiments, and MPPA-focused AI workloads.

Unified development toolkit for heterogeneous compute across GPU (ROCm), FPGA (Xilinx XRT/Vivado), MPPA (Kalray), and CPU targets. Provides cross-platform build tooling, device-specific runtime support, and early AI Agent integration.