One system from model evidence to edge execution.
Proton connects workload analysis, developer software, architecture simulation, evidence-gated engineering, and accelerator hardware into one measurable path for local AI.
Product family in architecture, prototype, and development stages
The platform is the product—not a disconnected chip and toolchain.
Modern edge inference depends on model formats, numerical behavior, compilers, runtimes, firmware, memory movement, and compute architecture working as one system. Proton is organized around that entire path.
- 01Workload evidence informs architecture
- 02Architecture constraints reshape software
- 03Verification evidence determines what advances
Quantization-native accelerator architecture.
Proton LPU-E0 is the current single-tile research direction: RISC-V control, vector and matrix execution, explicit local memory, DMA, and a practical host software path.
Research architecture; no production silicon exists.
A developer path from GGUF to a measurable device run.
The planned SDK brings together model inspection, llama.cpp and GGML integration, runtime APIs, kernel selection, profiling, and numerical comparison.
Choose the machine from workload behavior.
ProtonSim is intended to connect operator mix, tensor shapes, quantization, memory traffic, and execution regimes to traceable architecture decisions before RTL is frozen.
Agents accelerate iteration; evidence gates acceptance.
Forge coordinates specification, generation assistance, compilation, differential checks, randomized testing, coverage, regression analysis, and human review.
Every product produces inputs for the next decision.
Workload contracts, architecture models, compiled artifacts, reference comparisons, verification results, and review notes form the connective tissue across Proton.
- 01Traceable assumptions
- 02Versioned artifacts
- 03Independent checks
Status labels are part of the engineering contract.
Research, prototype, in-development, planned, and future labels separate current work from direction. They are intentionally visible throughout the site.