The Cursor SDK is Cursor’s TypeScript SDK for running coding agents programmatically. Use theDocumentation Index
Fetch the complete documentation index at: https://docs.honeyhive.ai/llms.txt
Use this file to discover all available pages before exploring further.
cursor-sdk-honeyhive cookbook to trace Cursor agent runs in HoneyHive. We plan to add first-class support through an instrumentor package soon.
One Cursor run becomes one HoneyHive session with the agent run, tool calls, and final assistant response.
Cursor’s TypeScript SDK is currently in public beta. Treat this cookbook workflow as experimental until package support is available.

Quick Start
You need Node.js 20+, pnpm, a Cursor API key, and a HoneyHive API key..env:
Add Tracing
Wrap any CursorAgent with traceRun:
HH_PROJECT, HH_SOURCE, and HH_API_URL to customize the project label, source label, or API endpoint. Set HH_API_URL for self-hosted or dedicated HoneyHive deployments.
What Gets Traced
Each Cursor run appears in HoneyHive as:| Event | Type | Notes |
|---|---|---|
session.start | session | Top-level container for the Cursor run. |
agent.run | chain | Cursor SDK invocation with the prompt, result, model, Git metadata, token usage, and step summaries. |
tool.<name> | tool | One event per Cursor tool call, such as tool.read, tool.glob, or tool.shell. |
turn.agent | model | Final assistant response with chat history and token usage metadata. |
Related
Cookbook source
Full runnable Cursor SDK tracing example
Enrich Your Traces
Add user IDs and custom metadata to Cursor SDK traces
Custom Spans
Create spans for business logic around agent calls
Tracing Quickstart
Get started with HoneyHive tracing

