Si2 Releases Public AI for EDA Ontology Repository for Agentic System Development

The Silicon Integration Initiative (Si2) AI/ML Schema/Ontology Working Group has announced the public release of its AI for EDA Ontology Repository. The repository supplies the semiconductor design community with an ontology and associated use cases to support experimentation with EDA agentic systems and industry collaboration.

Agentic AI systems are emerging in the semiconductor industry, which is shifting from point tools to autonomous workflows. Agentic EDA involves multi-step reasoning across design flows and requires context awareness, causal understanding, and workflow orchestration.

An ontology in EDA consists of a formal representation of concepts such as nets, cells, and timing paths; relationships such as “affects,” “depends on,” and “constrains”; and rules and constraints. It serves as the reasoning backbone for agentic systems by capturing workflow steps and dependencies, cause-and-effect relationships, design tradeoffs, and domain vocabulary and semantics.

The repository is available under the Apache 2.0 open-source license on GitHub at https://github.com/si2org/aiml_schema_ontology. It includes the EDA ontology in TTL/OWL format, documented and validated use cases developed by Arizona State University and Drexel University, ontology validation collateral, an MCP server for agent discovery and reasoning, a...