← Cursor changelog

Agent SDK

The Agent SDK has reached general availability, empowering users to define AI agents as code for a wide range of tasks. This release introduces a streamlined workflow for local development with an interactive playground, templates, and seamless deployment to Cursor's infrastructure. Agents support diverse triggers like GitHub, Slack, and webhooks, featuring consistent session management across conversations. A new GitHub PR replay tool significantly simplifies testing by converting real pull requests into local webhook payloads, alongside clearer evaluation definitions for comprehensive validation.

Source: official Cursor release notes. Summaries are written from the official notes; see how we work.

Changed

  • The Agent SDK is available today. It allows you to define an agent as a folder of code, test it with evals, and deploy it to Cursor or your own infrastructure.
  • Run `npx @cursor/agent-sdk init ./my-bot`, then `agent-sdk dev` to start the bot locally with a playground. Pass `--template` to start from a security reviewer, an owners-policy approver, a PR autofixer, or a Linear or Jira triager.
  • When you're ready to put an agent into use, you can deploy it to Cursor by running `agent-sdk deploy` from the project directory. The command builds the agent, gives it a URL, and starts it on our infrastructure. You can manage secrets and integrations from the dashboard, while continuing to use the same logs, evals, and playground available locally.
  • An agent is a project. `instructions.md` is the prompt. Each file in `tools/` is one typed action the model can call. `skills/` holds procedures the model loads on demand, `mcp-connections/` adds tools from MCP servers, and `channels/` defines where the bot receives and answers messages. `agent-sdk validate` checks the project and `agent-sdk info` prints what was discovered.
  • Agents wake on pull request, comment, and CI events from GitHub, GitLab, and Bitbucket; on mentions and DMs in Slack; on webhooks from any provider; and on a cron schedule. GitHub events pull through your Cursor account, so no public webhook URL is required. Slack is well-supported out of the box.
  • Each conversation keeps its own session and a complete record of every message and tool call. Follow-ups on a pull request or Slack thread resume the same session.
  • `agent-sdk github replay <pr-url>` turns a real pull request into signed webhook payloads and sends them to the bot, so GitHub-driven bots can be tested without waiting for a push. Add `--dry-run --fixtures-dir fixtures/` to save the payloads as eval fixtures.
  • The Agent SDK is generally available today. Read the docs and get started.

Fixed

  • An eval sends a fixed message to the bot and asserts on what it did: which tools ran, with what input, and the shape of the reply. Run `agent-sdk eval` locally or in CI.

Get notified the minute the next Cursor release ships

AI Drops sends a push with a plain-English summary of every release.

Get AI Drops on the App Store