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
fix docs/code discrepancies: add click coordinates, annotate extract, add --session
ShawnPana69902b713d44
diff --git a/browser_use/skill_cli/README.md b/browser_use/skill_cli/README.mdindex e385d6fe2..0ce332aea 100644--- a/browser_use/skill_cli/README.md+++ b/browser_use/skill_cli/README.md@@ -131,6 +131,7 @@ browser-use --cdp-url ws://localhost:9222/devtools/browser/... state| Command | Description ||---------|-------------|| `click <index>` | Click element by index |+| `click <x> <y>` | Click at pixel coordinates || `type "text"` | Type into focused element || `input <index> "text"` | Click element, then type || `keys "Enter"` | Send keyboard keys |@@ -185,7 +186,7 @@ browser-use --cdp-url ws://localhost:9222/devtools/browser/... state| Command | Description ||---------|-------------|| `eval "js code"` | Execute JavaScript |-| `extract "query"` | Extract data with LLM |+| `extract "query"` | Extract data with LLM (not yet implemented) |### Python (Persistent Session)```bashdiff --git a/skills/browser-use/SKILL.md b/skills/browser-use/SKILL.mdindex 0f11125bc..2b4006ba8 100644--- a/skills/browser-use/SKILL.md+++ b/skills/browser-use/SKILL.md@@ -57,7 +57,8 @@ browser-use screenshot # Take screenshot (base64)browser-use screenshot path.png # Save screenshot to file# Interactions (use indices from state)-browser-use click <index> # Click element+browser-use click <index> # Click element by index+browser-use click <x> <y> # Click at pixel coordinatesbrowser-use type "text" # Type into focused elementbrowser-use input <index> "text" # Click element, then typebrowser-use keys "Enter" # Send keyboard keys@@ -66,6 +67,7 @@ browser-use upload <index> <path> # Upload file to file input# Data Extractionbrowser-use eval "document.title" # Execute JavaScript+browser-use extract "query" # Extract data with LLM (not yet implemented)browser-use get text <index> # Get element textbrowser-use get html --selector "h1" # Get scoped HTML@@ -101,7 +103,8 @@ browser-use screenshot --full path.png # Full page screenshot### Interactions```bash-browser-use click <index> # Click element+browser-use click <index> # Click element by index+browser-use click <x> <y> # Click at pixel coordinatesbrowser-use type "text" # Type text into focused elementbrowser-use input <index> "text" # Click element, then type textbrowser-use keys "Enter" # Send keyboard keys@@ -118,6 +121,7 @@ Use indices from `browser-use state`.### JavaScript & Data```bashbrowser-use eval "document.title" # Execute JavaScript, return result+browser-use extract "query" # Extract data with LLM (not yet implemented)browser-use get title # Get page titlebrowser-use get html # Get full page HTMLbrowser-use get html --selector "h1" # Get HTML of specific element@@ -166,7 +170,7 @@ The Python session maintains state across commands. The `browser` object provide- `browser.goto(url)`, `browser.back()` — navigation- `browser.click(index)`, `browser.type(text)`, `browser.input(index, text)`, `browser.keys(keys)`, `browser.upload(index, path)` — interactions- `browser.screenshot(path)`, `browser.scroll(direction, amount)` — visual-- `browser.wait(seconds)`, `browser.extract(query)` — utilities+- `browser.wait(seconds)` — utilities### Cloud API```bash@@ -309,6 +313,7 @@ browser-use screenshot| `--profile [NAME]` | Use real Chrome (bare `--profile` uses "Default") || `--connect` | Auto-discover and connect to running Chrome via CDP || `--cdp-url <url>` | Connect to existing browser via CDP URL (`http://` or `ws://`) |+| `--session NAME` | Target a named session (default: "default") || `--json` | Output as JSON || `--mcp` | Run as MCP server via stdin/stdout |diff --git a/skills/remote-browser/SKILL.md b/skills/remote-browser/SKILL.mdindex acd66a107..721fc5a45 100644--- a/skills/remote-browser/SKILL.md+++ b/skills/remote-browser/SKILL.md@@ -65,7 +65,8 @@ browser-use screenshot # Take screenshot (base64)browser-use screenshot path.png # Save screenshot to file# Interactions (use indices from state)-browser-use click <index> # Click element+browser-use click <index> # Click element by index+browser-use click <x> <y> # Click at pixel coordinatesbrowser-use type "text" # Type into focused elementbrowser-use input <index> "text" # Click element, then typebrowser-use keys "Enter" # Send keyboard keys@@ -74,6 +75,7 @@ browser-use upload <index> <path> # Upload file to file input# Data Extractionbrowser-use eval "document.title" # Execute JavaScript+browser-use extract "query" # Extract data with LLM (not yet implemented)browser-use get text <index> # Get element textbrowser-use get html --selector "h1" # Get scoped HTML@@ -109,7 +111,8 @@ browser-use screenshot --full p.png # Full page screenshot### Interactions```bash-browser-use click <index> # Click element+browser-use click <index> # Click element by index+browser-use click <x> <y> # Click at pixel coordinatesbrowser-use type "text" # Type into focused elementbrowser-use input <index> "text" # Click element, then typebrowser-use keys "Enter" # Send keyboard keys@@ -126,6 +129,7 @@ Use indices from `browser-use state`.### JavaScript & Data```bashbrowser-use eval "document.title" # Execute JavaScript+browser-use extract "query" # Extract data with LLM (not yet implemented)browser-use get title # Get page titlebrowser-use get html # Get page HTMLbrowser-use get html --selector "h1" # Scoped HTML@@ -172,7 +176,7 @@ The Python session maintains state across commands. The `browser` object provide- `browser.goto(url)`, `browser.back()` — navigation- `browser.click(index)`, `browser.type(text)`, `browser.input(index, text)`, `browser.keys(keys)`, `browser.upload(index, path)` — interactions- `browser.screenshot(path)`, `browser.scroll(direction, amount)` — visual-- `browser.wait(seconds)`, `browser.extract(query)` — utilities+- `browser.wait(seconds)` — utilities### Tunnels```bash@@ -220,6 +224,7 @@ browser-use screenshot| `--profile [NAME]` | Use real Chrome (bare `--profile` uses "Default") || `--connect` | Auto-discover and connect to running Chrome via CDP || `--cdp-url <url>` | Connect to existing browser via CDP URL (`http://` or `ws://`) |+| `--session NAME` | Target a named session (default: "default") || `--json` | Output as JSON |## Command Chaining