# Introducing the Agent SDK

Source: [Cursor](https://cursor.com/blog/agent-sdk)  
Feed7 permalink: https://feed7.dev/p/agent-sdk-1y8likr  
Published: 2026-10-20T12:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Cursor’s Agent SDK lets teams define, evaluate, and deploy event-driven agents as code, with local evals, event replay, subagents, and an option to run on their own infrastructure.

## Source Summary

Cursor’s **Agent SDK** is generally available for building agents in code and deploying them to Cursor infrastructure with `agent-sdk deploy`. An agent project includes Markdown instructions, TypeScript tools, external connections, and evals; it can also run as a Node process in a container.

## Practical Implication

Builders can use it to automate team workflows such as PR review, then version and review the agent like other software. The SDK includes evals and event replay, and agents can delegate work to specialized agents or parallel subagents.

## Agent-Ready Context

Cursor’s **Agent SDK** is generally available for building agents in code and deploying them to Cursor infrastructure with `agent-sdk deploy`. An agent project includes Markdown instructions, TypeScript tools, external connections, and evals; it can also run as a Node process in a container.

Builders can use it to automate team workflows such as PR review, then version and review the agent like other software. The SDK includes evals and event replay, and agents can delegate work to specialized agents or parallel subagents.

The source describes one internal knowledge-base reviewer built in about a day, but gives no general build-time estimate. Deployment to Cursor is one option; self-hosting is also supported, with infrastructure and operational details left to the docs.

## Connected Context

Feed7 judgment across 928 accumulated Signals:

Cursor’s SDK packages agent instructions, tools, connections, evals, replay, and deployment or self-hosting options into a versionable project. It adds a concrete build-and-operate path for team workflows, while the single internal example does not establish general implementation time or comparative performance.

- [How Notion used the Cursor SDK to embed coding agents](https://feed7.dev/p/notion-07d02so) — Notion’s deployment shows a product embedding built with the Cursor SDK; this announcement describes the SDK’s broader project structure, evals, replay, and deployment options.
- [Cursor is now available in the AI SDK harness layer](https://feed7.dev/p/cursor-ai-sdk-harness-adapter-0nbmzmh) — The SDK is a way to build and deploy Cursor agents, while the HarnessAgent adapter makes Cursor one runtime behind a shared interface; the latter does not establish feature parity with the SDK.
- [The Prime Intellect Stack — Will Brown, Prime Intellect](https://feed7.dev/p/the-prime-intellect-stack-will-brown-prime-intellect-1dc0rrp) — Both emphasize evals in agent infrastructure; Cursor includes evals and event replay in its SDK, while Prime Intellect describes composable environments and an interceptor for existing harnesses.

## Context Map

- Layer: tools
- Domains: coding
- Topics: agent-sdks, agent-evals, subagents

## Uncertainty

- The source describes one internal knowledge-base reviewer built in about a day, but gives no general build-time estimate. Deployment to Cursor is one option; self-hosting is also supported, with infrastructure and operational details left to the docs.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.