docs/tools/browser-login.md
When a site requires login, sign in manually in the host browser's openclaw
profile. Do not give the model your credentials: automated logins often
trigger anti-bot defenses and can lock the account.
Use the host browser (manual login) for both reading (search/threads) and posting on X/Twitter and other bot-sensitive sites. Sandboxed browser sessions are more likely to trigger bot detection.
Back to the main browser docs: Browser.
OpenClaw controls a dedicated Chrome profile named openclaw (orange-tinted
UI), separate from your daily browser profile.
For agent browser tool calls:
openclaw browser.profile="user" only when existing logged-in sessions matter and you
are at the computer to click/approve any attach prompt.Two ways to access the openclaw profile:
openclaw browser start
openclaw browser open https://x.com
For a non-default profile, put --browser-profile <name> before the
subcommand (default is openclaw):
openclaw browser --browser-profile <name> open https://x.com
If the agent is sandboxed, its browser tool calls default to the sandbox
browser, not the host. To let the agent target the host browser instead:
{
agents: {
defaults: {
sandbox: {
mode: "non-main",
browser: {
allowHostControl: true,
},
},
},
},
}
CLI invocations always target the host browser, never the sandbox, so you can open the host browser yourself regardless of this setting:
openclaw browser --browser-profile openclaw open https://x.com
Once sandbox.browser.allowHostControl: true is set, the agent's browser
tool calls can target the host too. Alternatively, disable sandboxing for the
agent that posts updates.