Moss builds a high-performance runtime for real-time semantic search in conversational AI. Built in Rust and WebAssembly, it delivers sub-10ms lookup times and runs search and embedding inside the application process with no network hop on the hot path, enabling voice agents, copilots, and chat interfaces to retrieve, reason, and respond instantly. Moss offers hybrid retrieval (semantic plus keyword), built-in embeddings, and metadata filtering from a single SDK that runs in browsers, on-device, at the edge, and in the cloud. The company is part of Y Combinator's Fall 2025 batch.