Introducing OpenCores: From Prompt to Silicon
March 13, 2026 · OpenCores Team
We're excited to introduce OpenCores — an AI-native platform that turns natural language into fabrication-ready chip designs.
Why We Built This
Chip design has been locked behind $50M budgets and multi-year timelines. Only about 20 companies worldwide can afford custom silicon. Meanwhile, the semiconductor talent gap is widening, with 300,000+ unfilled positions globally.
We believe AI can change this equation fundamentally.
How It Works
OpenCores uses a custom fine-tuned model trained on over 25,000 verified VHDL and Verilog designs. When you describe a circuit in plain English, our AI generates synthesizable HDL code, creates testbenches, and runs verification through 6 autonomous testing agents.
Claude 4.6 serves as the orchestration layer, managing the multi-step reasoning pipeline from specification to synthesis.
The result? A complete design flow from natural language to GDSII layout, using OpenLane2 and the SKY130 PDK.
What's Next
We're continuously improving our model, expanding PDK support, and building collaboration features. Our goal is to make chip design as accessible as writing software.
If you're a researcher, student, or engineer interested in chip design, we'd love to have you try OpenCores. Sign up at opencores.ai.