Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
Python ai-agentsai-toolsbrowser-agentbrowser-automationbrowser-usecdpcloud-browsercomputer-useheadless-browserllmmcpplaywrightpythonremote-browserstealth-browserweb-automationweb-scraping
Release 0.13.7 with Browser Harness 0.1.8
Laith Weinberger449e9ad5b97d
diff --git a/browser_use/skills/browser-use/SKILL.md b/browser_use/skills/browser-use/SKILL.mdindex d0e8f950c..039209a21 100644--- a/browser_use/skills/browser-use/SKILL.md+++ b/browser_use/skills/browser-use/SKILL.md@@ -7,6 +7,10 @@ description: "Direct browser control via CDP for web interaction: automation, scDirect browser control via CDP. For task-specific edits, use `agent-workspace/agent_helpers.py`. For setup, install, or connection problems, read https://github.com/browser-use/browser-harness/blob/main/install.md.+## When Not to Use++A basic fetch of public information needs no browser. If a plain HTTP request can read it — a public page, an API, docs — use `curl` or your fetch tool, and leave the browser alone. Use browser-use when the task needs interaction (click, type, navigate), the user's logged-in session, JS rendering, or a bot-protected page. If a direct fetch fails or returns a shell page, then escalate to the browser.+Domain skills are off by default. Set `BH_DOMAIN_SKILLS=1` to enable them; see the bottom section.**If `BH_DOMAIN_SKILLS=1` and the task is site-specific, read every file in the matching `$BH_AGENT_WORKSPACE/domain-skills/<site>/` directory before inventing an approach.**@@ -32,7 +36,9 @@ If the daemon cannot connect, run diagnostics:browser-use --doctor```-If Chrome remote debugging is not enabled, the harness opens:+If Chrome is not running at all, the harness launches it automatically and retries — no user action needed beyond clicking Allow if a permission popup appears.++If Chrome is running but remote debugging is not enabled, the harness opens:```textchrome://inspect/#remote-debugging@@ -154,7 +160,7 @@ If you get stuck on a browser mechanic, check https://github.com/browser-use/bro## Gotchas- `chrome://inspect/#remote-debugging` must be enabled for local Chrome control.-- Chrome may show an "Allow remote debugging?" popup; wait for the user to click Allow.+- Chrome may show an "Allow remote debugging?" popup; wait for the user to click Allow. Do not retry in a loop — Chrome pops a fresh dialog for every new connection, and the daemon's single held connection is what makes this a one-time click.- Omnibox popups are not real work tabs.- CDP target order is not Chrome's visible tab-strip order.- `BU_CDP_URL` is an HTTP DevTools endpoint; the daemon resolves it to WebSocket.diff --git a/pyproject.toml b/pyproject.tomlindex de74767b8..92f970dea 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -2,7 +2,7 @@name = "browser-use"description = "Make websites accessible for AI agents"authors = [{ name = "Gregor Zunic" }]-version = "0.13.6"+version = "0.13.7"readme = "README.md"requires-python = ">=3.11,<4.0"classifiers = [@@ -46,7 +46,7 @@ dependencies = ["markdownify==1.2.2","python-docx==1.2.0","browser-use-sdk==3.4.2",- "browser-harness==0.1.6",+ "browser-harness==0.1.8",]# google-api-core: only used for Google LLM APIs# pyperclip: only used for examples that use copy/pastediff --git a/skills/browser-use/SKILL.md b/skills/browser-use/SKILL.mdindex d0e8f950c..039209a21 100644--- a/skills/browser-use/SKILL.md+++ b/skills/browser-use/SKILL.md@@ -7,6 +7,10 @@ description: "Direct browser control via CDP for web interaction: automation, scDirect browser control via CDP. For task-specific edits, use `agent-workspace/agent_helpers.py`. For setup, install, or connection problems, read https://github.com/browser-use/browser-harness/blob/main/install.md.+## When Not to Use++A basic fetch of public information needs no browser. If a plain HTTP request can read it — a public page, an API, docs — use `curl` or your fetch tool, and leave the browser alone. Use browser-use when the task needs interaction (click, type, navigate), the user's logged-in session, JS rendering, or a bot-protected page. If a direct fetch fails or returns a shell page, then escalate to the browser.+Domain skills are off by default. Set `BH_DOMAIN_SKILLS=1` to enable them; see the bottom section.**If `BH_DOMAIN_SKILLS=1` and the task is site-specific, read every file in the matching `$BH_AGENT_WORKSPACE/domain-skills/<site>/` directory before inventing an approach.**@@ -32,7 +36,9 @@ If the daemon cannot connect, run diagnostics:browser-use --doctor```-If Chrome remote debugging is not enabled, the harness opens:+If Chrome is not running at all, the harness launches it automatically and retries — no user action needed beyond clicking Allow if a permission popup appears.++If Chrome is running but remote debugging is not enabled, the harness opens:```textchrome://inspect/#remote-debugging@@ -154,7 +160,7 @@ If you get stuck on a browser mechanic, check https://github.com/browser-use/bro## Gotchas- `chrome://inspect/#remote-debugging` must be enabled for local Chrome control.-- Chrome may show an "Allow remote debugging?" popup; wait for the user to click Allow.+- Chrome may show an "Allow remote debugging?" popup; wait for the user to click Allow. Do not retry in a loop — Chrome pops a fresh dialog for every new connection, and the daemon's single held connection is what makes this a one-time click.- Omnibox popups are not real work tabs.- CDP target order is not Chrome's visible tab-strip order.- `BU_CDP_URL` is an HTTP DevTools endpoint; the daemon resolves it to WebSocket.