agent-browser

分类: 工具与效率 | 上传者: itechmeat | 下载: 0 | 版本: v1.0（最新）

Headless browser automation CLI for AI agents. Covers commands, refs, sessions, snapshots, cloud providers, profiles. Use when automating browser interactions, navigating pages, filling forms, taking screenshots, extracting data, or testing web applications programmatically. Keywords: agent-browser, browser automation, refs, snapshot.

更新日志: Source: GitHub https://github.com/itechmeat/llm-code

目录结构

当前层级: skills/agent-browser/

📁 references/
- 📄 advanced.md 7.3 KB
- 📄 commands.md 7.0 KB
- 📄 installation.md 790 B
- 📄 refs.md 2.2 KB
📄 SKILL.md 5.8 KB

SKILL.md

---
name: agent-browser
description: "Headless browser automation CLI for AI agents. Covers commands, refs, sessions, snapshots, cloud providers, profiles. Use when automating browser interactions, navigating pages, filling forms, taking screenshots, extracting data, or testing web applications programmatically. Keywords: agent-browser, browser automation, refs, snapshot."
metadata:
  version: "0.17.0"
  release_date: "2026-03-08"
---

# Agent Browser

Headless browser automation CLI for AI agents. Fast Rust CLI with Node.js fallback.

Works with: Claude Code, Cursor, GitHub Copilot, OpenAI Codex, Google Gemini, opencode.

## Quick Navigation

| Topic        | Reference                                     |
| ------------ | --------------------------------------------- |
| Installation | [installation.md](references/installation.md) |
| Commands     | [commands.md](references/commands.md)         |
| Refs         | [refs.md](references/refs.md)                 |
| Advanced     | [advanced.md](references/advanced.md)         |

## When to Use

- Automating browser tasks in AI agent workflows
- Web scraping with AI-friendly output
- Testing web applications with LLM agents
- Managing multiple browser sessions with isolated auth

## Core Concepts

### Refs (Element References)

The `snapshot` command returns an accessibility tree where each element has a unique ref like `@e1`, `@e2`:

- **Deterministic** - ref points to exact element from snapshot
- **Fast** - no DOM re-query needed
- **AI-friendly** - LLMs can reliably parse and use refs

### Architecture

Client-daemon architecture:

1. **Rust CLI** - parses commands, communicates with daemon
2. **Daemon** - runs the browser automation engine:
   - Default: **Node.js daemon** (Playwright)
   - Native (v0.16.0+): **native Rust daemon** (direct Chrome DevTools Protocol), enabled via `--native`, `AGENT_BROWSER_NATIVE=1`, or `"native": true`
   - Lightpanda (v0.17.0+): **Lightpanda engine**, selected via `--engine lightpanda` or `AGENT_BROWSER_ENGINE=lightpanda` (implies native mode)

Daemon starts automatically and persists between commands. Startup errors are surfaced directly (v0.17.0+).

v0.8.6 improves daemon reliability by cleaning stale socket/PID files and retrying transient connection errors.

## Quick Example

```bash
# Navigate and get snapshot
agent-browser open example.com
agent-browser snapshot                    # Get accessibility tree with refs
agent-browser click @e2                   # Click by ref from snapshot
agent-browser fill @e3 "test@example.com" # Fill input by ref
agent-browser get text @e1                # Get text by ref
agent-browser screenshot page.png         # Save screenshot
agent-browser close
```

## AI Workflow Pattern

Optimal workflow for AI agents:

```bash
# 1. Navigate and get snapshot
agent-browser open example.com
agent-browser snapshot -i --json   # AI parses tree and refs

# 2. AI identifies target refs from snapshot

# 3. Execute actions using refs
agent-browser click @e2
agent-browser fill @e3 "input text"

# 4. Get new snapshot if page changed
agent-browser snapshot -i --json
```

## Headed Mode (Debugging)

```bash
agent-browser open example.com --headed
```

## Local File Access (v0.9.1)

```bash
agent-browser open file:///path/to/doc.pdf --allow-file-access
```

## Cursor-Aware Snapshots (v0.9.1)

```bash
agent-browser snapshot -C
agent-browser snapshot --cursor
```

## Session Persistence (v0.10.0)

Automatically save and restore cookies/localStorage across restarts with a named session:

```bash
agent-browser --session-name myapp open myapp.com
agent-browser --session-name myapp open myapp.com
```

State management commands:

```bash
agent-browser state list
agent-browser state show myapp
agent-browser state rename myapp myapp-prod
agent-browser state clear myapp-prod
agent-browser state cleanup
```

## Release Updates (v0.12.0–v0.14.0)

- Added `keyboard` commands for raw keyboard input at the currently focused element (no selector needed).
- Added persistent color scheme selection via `--color-scheme` and `AGENT_BROWSER_COLOR_SCHEME`.
- Improved IPC reliability (EAGAIN/backpressure-aware writes) and lowered default Playwright timeout to 25s (configurable via `AGENT_BROWSER_DEFAULT_TIMEOUT`).
- Improved CDP reconnection and fixed state load when no browser is running.
- Reduced `--annotate` warning noise when the flag isn’t explicitly passed.

## New Tab Clicks (v0.10.0)

```bash
agent-browser click @e12 --new-tab
```

## Mobile Safari (iOS)

```bash
agent-browser -p ios device list
agent-browser -p ios open https://example.com --device "iPhone 15"
agent-browser tap 200 400
agent-browser swipe 200 600 200 200 500
```

## JSON Output

Use `--json` for machine-readable output:

```bash
agent-browser snapshot --json
agent-browser get text @e1 --json
agent-browser is visible @e2 --json
```

## Critical Prohibitions

- Do not use CSS/XPath selectors when refs are available (use @e1, @e2, etc.)
- Do not forget to close sessions when done
- Do not assume element positions without taking a fresh snapshot
- Do not use old refs after page navigation or content changes (re-snapshot)

## Common Commands

```bash
# Navigation
agent-browser open <url>
agent-browser back / forward / reload
agent-browser close

# Interaction
agent-browser click <sel>
agent-browser click <sel> --new-tab
agent-browser fill <sel> <text>
agent-browser press <key>
agent-browser hover <sel>
agent-browser select <sel> <val>
agent-browser download <sel> <path>  # v0.7+

# Info
agent-browser get text <sel>
agent-browser get url
agent-browser get title
agent-browser is visible <sel>

# Snapshots & Screenshots
agent-browser snapshot -i --json
agent-browser screenshot [path]
```

## Links

- [Documentation](https://agent-browser.dev/)
- [Changelog](https://agent-browser.dev/changelog)
- [GitHub](https://github.com/vercel-labs/agent-browser)
- [npm](https://www.npmjs.com/package/agent-browser)

登录后下载/点赞/收藏 ❤ 8 | ★ 0

agent-browser

目录结构

SKILL.md

举报内容

提示