@cursor/july
v0.6.0
Published
Build, test, and deploy agents as code on Cursor's agent harness.
Readme
Agent SDK
Agent SDK is how Cursor builds bots and agents. It is the open-source version of the engine behind Bugbot, Security Review, Approval Bot, and Rollouts.
An Agent SDK project is a folder of Markdown and TypeScript. Combine model judgment with deterministic code, then make the result available in source control, Slack, issue trackers, and Cursor.
Why use it
Bots and agents live in your repo. Review, version, and ship instructions, tools, and evals with the rest of your code.
Cursor runs the loop. Your project gets Cursor's models, tool calling, skills, MCP, and subagents.
Use it where you work. Trigger a project from source-control events, Slack threads, custom webhooks, or schedules.
Test normal TypeScript. Add evals and unit tests without a separate configuration language.
Choose where it runs. Deploy to Cursor-managed hosting or run the process on your infrastructure.
When to use Agent SDK
| | Cursor Automations | Grok Bot | Agent SDK | | --- | --- | --- | --- | | Use for | Repeatable jobs driven by a prompt and trigger | Interactive agents you work with in Cursor | Agents that need custom code, integrations, tests, or deployment choices | | 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 an agent without creating a software project | You want deterministic code around model judgment and a project your team can review and test |
Get started
Agent SDK requires Node 22.13 or newer. Install @grok/agent-sdk, create a
project, and start the development server:
npm install --global @grok/agent-sdk
agent-sdk init ./my-bot
cd my-bot
agent-sdk devFor a one-off scaffold without a global install:
npx @grok/agent-sdk init ./my-botOpen the project in Cursor. Agent SDK uses bot/ for the agent and keeps
evals/ at the project root:
my-bot/
├── package.json
├── bot/
│ ├── agent.ts
│ ├── instructions.md
│ ├── tools/
│ ├── skills/
│ ├── mcp-connections/
│ ├── subagents/
│ ├── channels/
│ ├── hooks/
│ └── schedules/
└── evals/Describe the bot or agent in Cursor, or edit the files yourself.
Start from a template
Pass a template to agent-sdk init when one matches your goal:
| Template | Capability |
| --- | --- |
| security-reviewer | Review pull requests for exploitable bugs |
| thermo-quality-review | Review structural code quality |
| thermo-review | Review bugs and breakage |
| agentic-owners | Apply owners policies to pull requests |
| triage-linear or triage-jira | Triage tracker issues |
agent-sdk init ./security-reviewer --template security-reviewer--template triage selects triage-linear.
Next steps
Run agent-sdk docs to open the full documentation. By default,
agent-sdk serve also serves the same documentation at /docs.
The docs include:
- A complete PR reviewer quickstart
- GitHub, Slack, webhook, and MCP guides
- Evals and hillclimbing
- Deployment and troubleshooting
- Project layout, CLI, and API reference
