Cursor Agent SDK: Build, Test, and Deploy AI Agents as Code

Cursor released the Agent SDK, which lets developers define AI agents as folders of Markdown and TypeScript, test them with evals, and deploy them to managed or self-hosted infrastructure. The SDK packages agent definition, evaluation and deployment into a code-based workflow.

Cursor's new Agent SDK lets you define AI agents as folders of Markdown and TypeScript, test them with evals, and deploy to managed or self-hosted infrastructure. The post Cursor Agent SDK: Build, Test, and Deploy AI Agents as Code appeared first on byteiota .