| name | opensteer |
| description | Direct browser control via CDP. Use when the user wants to automate, inspect, scrape, test, or interact with web pages. |
Opensteer
Opensteer is a global browser-control runtime. It exposes small CDP primitives to agents and harness packs.
Usage
opensteer -c "print(page_info())"
Python snippets run with helpers pre-imported:
opensteer -c "new_tab('https://docs.opensteer.com'); wait_for_load(); print(page_info())"
For harness code, import helpers from the installed package:
from opensteer.helpers import goto_url, js, click_at_xy, type_text, wait_for_load
Named Sessions
Use OPENSTEER_NAME to route commands to a named browser session:
OPENSTEER_NAME=linkedin opensteer -c "print(page_info())"
Remote browser sessions can be started from a Python snippet when OPENSTEER_API_KEY is set:
opensteer -c "start_remote_daemon('linkedin', profileId='bp_...')"
OPENSTEER_NAME=linkedin opensteer -c "new_tab('https://example.com')"
Browser Profiles
A browser profile is a saved, logged-in browser identity (cookies, auth state)
a cloud browser can launch with. Profile access is grant-based: the server
tracks which profiles this agent may use, and there is no per-agent default
profile.
list_cloud_profiles() lists visible profiles; each entry carries a
granted flag saying whether this agent may use it.start_remote_daemon(name) without a profile lets the server resolve it:
exactly one granted profile auto-attaches, none launches a fresh signed-out
session, and several granted profiles is rejected with an error telling you
to pass profileName or profileId.- When several profiles are granted, pick one explicitly:
start_remote_daemon('linkedin', profileName='LinkedIn work') or
start_remote_daemon('linkedin', profileId='bp_...'). Durable scripts
should pin profileId — it survives profile renames.
- Passing a profile that is not granted to this agent fails with a 403 whose
message says how to proceed (list granted profiles or request access).
Interaction Skills
Generic browser mechanics live in interaction-skills/:
- connection.md
- cookies.md
- cross-origin-iframes.md
- dialogs.md
- downloads.md
- drag-and-drop.md
- dropdowns.md
- iframes.md
- network-requests.md
- print-as-pdf.md
- screenshots.md
- scrolling.md
- shadow-dom.md
- tabs.md
- uploads.md
- viewport.md
Use them when a page mechanic is tricky. Put domain-specific selectors, workflows, APIs, local databases, and task tools in the harness pack.
What Works Well
- Start with screenshots for visible state:
capture_screenshot().
- Prefer coordinate clicks for visible targets:
click_at_xy(x, y).
- Use
js(...) for DOM inspection, extraction, and page API discovery.
- Use
cdp("Domain.method", ...) for raw CDP operations not covered by helpers.
- After navigation, call
wait_for_load().
- Navigate the current Opensteer-owned tab by default; use
list_tabs() and switch_tab(target_id) only when the user explicitly asks for a specific existing tab.
- If a page redirects to login, stop and ask the user. Do not type credentials from screenshots.
Boundaries
Opensteer owns generic browser primitives, local attach, remote attach, cloud browser attach, and generic interaction skills.
Harness packs own domain-specific tools, selectors, workflows, storage, setup docs, and agent skills.
