Agentic WeeklyGet the weekly

Cursor's Agent SDK is generally available: agents as code, with evals and one-command deploys

Release Ruler for this brief: marked at its publication date, Oct 27, 2026, among the AI models we track.

Cursor's Agent SDK, generally available as of Cursor's October 2026 announcement, lets teams define an agent as a project folder (Markdown instructions, TypeScript tools, skills, MCP connections, channels), test it with evals, and deploy it to Cursor's infrastructure with agent-sdk deploy or run it as a single Node process on their own servers.

By Agentic Weekly · Evidence: Reported · How we work

First seen
(via X: @cursor_ai announcement)
Source published
(we saw it 17.2 hours later)
Brief published

What changed

  • Cursor says the Agent SDK is the framework it uses to build its own managed agents, Bugbot, Security Reviewer and Rollouts, and that it is generally available. Cursor's blog post is dated October 20, 2026; Cursor announced it on X on October 26, 2026.
  • An agent is a project: instructions.md is the prompt, each file in tools/ is one typed TypeScript action, skills/ holds procedures loaded on demand, mcp-connections/ adds tools from MCP servers, and channels/ defines where the bot receives and answers messages.
  • Channels: agents wake on pull request, comment and CI events from GitHub, GitLab and Bitbucket, on Slack mentions and DMs, on webhooks from any provider, and on a cron schedule. Each conversation keeps its own session and a full record of messages and tool calls.
  • Evals: an eval sends a fixed message and asserts which tools ran, with what input, and the shape of the reply; agent-sdk eval runs locally or in CI, and agent-sdk github replay turns a real pull request into signed webhook payloads for testing.
  • Deploy: agent-sdk deploy builds the agent, gives it a URL and runs it on Cursor's infrastructure; Cursor says it can also run on your own infrastructure as a single Node process that can be packaged in a container.
  • Quick start from the changelog: run npx @cursor/agent-sdk init ./my-bot, then agent-sdk dev for a local playground. --template starts from a security reviewer, an owners-policy approver, a PR autofixer, or a Linear or Jira triager. agent-sdk validate checks the project and agent-sdk info prints what was discovered.

In the source’s words

“Today, we're releasing the Agent SDK, the framework we use to build our own managed agents like Bugbot, Security Reviewer, and Rollouts.”

Early verdict

Best for teams that want PR-review, triage or compliance bots kept in version control with evals, especially if they already use Cursor; check hosted pricing before relying on Cursor-run deploys.

Basis: Based only on the features Cursor's blog post and changelog describe; we have not built or run an agent with the SDK.

What we have not verified

  • We did not install the SDK, run the templates or deploy an agent.
  • Neither the blog post nor the changelog states pricing for agents hosted on Cursor's infrastructure or which Cursor plans include hosted deploys.
  • The package licence and source availability are not stated in the pages we read.

This brief is Reported: written from the sources below, not from running the release ourselves.

Sources

Spotted an error? See our corrections policy or email the address on the contact page. Markdown version for agents: /news/cursor-agent-sdk-ga-agents-as-code.md

Want these briefs in your Google Top Stories? Add Agentic Weekly as a preferred source on Google.