# Agent SDK

Agent SDK lets you define, test, evaluate, and deploy agents as code. It uses the Cursor SDK harness
that powers Bugbot, Security Review, Approval Bot, and Rollouts.

An Agent's behavior is defined in a folder of Markdown and TypeScript that combines deterministic
code with model judgment. Agent SDK makes it easy to build useful agents, with APIs to interact on
Slack, pull requests, issue trackers, Cursor, and the other places where you get work done.

After you deploy an agent, open [Deployed Agents](https://cursor.com/dashboard/deployed-agents) to
manage it.

## Get Started with your Coding Agent

Paste this prompt into your coding agent. It installs the CLI, asks what your agent is for,
scaffolds and checks a first project, and tells you how to test and deploy it.

```text
Set up my first Agent SDK project.

Read https://cursor.com/docs/agent-sdk.md. Add .md to any page under
https://cursor.com/docs/agent-sdk/ to read it as Markdown.

1. Check that Node is 22.13 or newer, then run:
   npm install --global @grok/agent-sdk
2. Follow the agent-sdk-create-agent skill at
   "$(npm root -g)/@grok/agent-sdk/skills/create-agent/SKILL.md".
3. Do not deploy or push until I ask. End by telling me what the agent
   does, how to test it locally, and how to deploy it.
```

## Why Agent SDK

Your instructions, tools, and evals are files you review, test, and version like the rest of your
code. You write the instructions and tools, and Cursor runs the model loop that calls them.

## When to use Agent SDK

|                    | Cursor Automations                            | Grok Bot                                                        | Agent SDK                                                                                          |
| ------------------ | --------------------------------------------- | --------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
| **You define**     | A prompt, model, and trigger in the dashboard | Instructions, skills, and connected tools in the app            | A versioned Markdown and TypeScript project                                                        |
| **Where it runs**  | Cursor-managed                                | Cursor-managed                                                  | Cursor-managed hosting or your infrastructure                                                      |
| **Choose it when** | The job fits a schedule or event trigger      | You want to configure and talk to an agent without writing code | You want code around model judgment that your team can version control, review, test and hillclimb |

## Get started

Install `@grok/agent-sdk`, then scaffold and run a project. The package was `@cursor/bdk` before.

```bash
npm install --global @grok/agent-sdk
agent-sdk init ./my-bot
cd my-bot
agent-sdk dev
```

[Project layout](/docs/reference/project-layout.md) explains every folder under `bot/`.

## Next steps

- [Build your first PR reviewer agent](/docs/quickstart.md) step by step.
- Start from a [review or triage template](/docs/templates/reviews.md) or the
  [owners-policy approver](/docs/templates/agentic-owners.md).
- [Convert a Cursor Automation](/docs/guides/convert-automation.md) into an Agent SDK project.
- [Build agents with agents](/docs/building-with-agents.md) using a coding agent.
- Look up commands in the [CLI reference](/docs/reference/cli.md) and deployed-agent roles in
  [Access](/docs/reference/access.md).

## Architecture

![Agent SDK architecture](/docs/architecture.svg)
