OpenErrand documentation
A universal, safe way to run actions in a real browser — for yourself, or for your users. Start with the quickstart; everything else is here when you need it.
Get started
QuickstartThe easiest way to add OpenErrand is to let your AI coding tool set it up.
Integration Guide — zero to first taskThis is the developer front door — for a product that wants to run a browser action for
Pairing — connect a user's browserBefore OpenErrand can run an errand for one of your users, that user's browser must be
Author an errand with an LLM coding toolWhen recording isn't an option, let your coding assistant (Claude Code, Cursor, etc.)
Quickstart: driving a task with an LLMOpenErrand is "the pipe" — you bring the intelligence.
How it works
OBEP Security ModelThis document states the trust model plainly so a customer's security team can
The Open/Closed Boundary (OBEP vs OpenErrand)Governing rule: anything whose secrecy would create a vulnerability MUST be
OBEP Error TaxonomyStable error codes carried on status messages (phase: "error", code).
Run & deploy
Trust & legal
Reading this as a machine? Grab /llms.txt · /llms-full.txt — or any page as /docs/<name>.md.