Most progress in AI comes from scaling models. Rome scales the other axis: the environment—the tools, workflows, memory, and interfaces an agent works within.

Rome is a guardrailed environment where humans and agents collaborate, and that collaboration compounds. Proven capabilities stick, so every interaction can raise the ceiling for the next.

My work spans the agent runtime, Rome Apps and developer tooling, Rome Cloud, native experiences, and the open-source ecosystem around them.

Before Rome, I worked on Web Infra at ByteDance and helped build the open-source tooling ecosystem around Rspack, Rsbuild, Rspress, Rsdoctor, Rslib, and Rstest.