专为本地 LLM 设计的 Token 高效浏览器代理 — Playwright + 辅助功能树 + MarkGrab，原生支持 MCP。
browsegrab 是一个轻量级浏览器自动化库，专为本地 LLM（8B-35B 参数）设计。它结合了 Playwright 的辅助功能树和 MarkGrab 的 HTML 转 Markdown 功能，与 browser-use 等替代方案相比，每步 Token 消耗减少了 5-8 倍。
Token 高效：每步约 500-1,500 个 Token（相比 browser-use 的 4,000-10,000 个）
本地 LLM 优先：针对 vLLM、Ollama 和兼容 OpenAI 的端点进行了优化
原生支持 MCP：内置 MCP 服务器，包含 8 个浏览器自动化工具
集成 MarkGrab：HTML → 简洁的 Markdown，用于内容提取
辅助功能树 + 引用系统：稳定的元素引用（e1, e2, ...），无需视觉模型
成功模式缓存：重复工作流无需调用 LLM
5 阶段 JSON 解析器：针对本地 LLM 输出的稳健动作解析
最小依赖：核心仅依赖 playwright + httpx
Related MCP server: Playwright MCP Server
pip install browsegrab
playwright install chromium可选功能：
pip install browsegrab[mcp] # MCP server support
pip install browsegrab[content] # MarkGrab content extraction
pip install browsegrab[cli] # CLI with rich output
pip install browsegrab[all] # Everythingfrom browsegrab import BrowseSession
async with BrowseSession() as session:
# Navigate and get accessibility tree snapshot
await session.navigate("https://example.com")
snap = await session.snapshot()
print(snap.tree_text)
# - heading "Example Domain" [level=1]
# - link "Learn more": [ref=e1]
# Click using ref ID
result = await session.click("e1")
print(result.url) # https://www.iana.org/help/example-domains
# Type into search box
await session.navigate("https://en.wikipedia.org")
snap = await session.snapshot()
await session.type("e4", "Python programming", submit=True)
# Extract compressed content (AX tree + markdown)
content = await session.extract_content()# Accessibility tree snapshot
browsegrab snapshot https://example.com
# JSON output
browsegrab snapshot https://example.com -f json
# Extract content (AX tree + markdown)
browsegrab extract https://en.wikipedia.org/wiki/Python
# Agentic browse (requires LLM endpoint)
browsegrab browse https://example.com "Find the about page"browsegrab-mcp # Start MCP server (stdio)Claude Desktop / Cursor / VS Code 配置：
{
"mcpServers": {
"browsegrab": {
"command": "browsegrab-mcp"
}
}
}8 个 MCP 工具：browser_navigate, browser_click, browser_type, browser_snapshot, browser_scroll, browser_extract_content, browser_go_back, browser_wait
flowchart LR
A["🌐 URL + Goal"] --> B["Navigate"]
B --> C["AX Tree Snapshot\n~200–500 tokens"]
C --> D{"LLM\nDecision"}
D -->|"click / type / scroll"| E["Execute Action"]
E --> C
D -->|"goal reached"| F["Extract Content\n(MarkGrab)"]
F --> G["✅ Result"]browsegrab 将结构（辅助功能树）与内容（MarkGrab Markdown）分离，仅发送 LLM 所需的信息：
flowchart TD
A["Raw HTML"] --> B["Accessibility Tree"]
A --> C["MarkGrab Markdown"]
B --> D["Structure: ~200–500 tokens\nInteractive elements with ref IDs"]
C --> E["Content: ~300–800 tokens\nClean markdown · on-demand"]
D --> F["Combined: ~500–1,300 tokens/step\n⚡ 5–8× fewer than browser-use"]
E --> F页面 | 交互元素 | Token 数 | browser-use 等效值 |
example.com | 1 | ~60 | ~500+ |
维基百科文章 | 452 | ~1,254 | ~10,000+ |
browsegrab/
├── config.py # Dataclass configs (env var loading)
├── result.py # Result types (ActionResult, BrowseResult, ...)
├── session.py # BrowseSession orchestrator
├── browser/
│ ├── manager.py # Playwright lifecycle (async context manager)
│ ├── snapshot.py # Accessibility tree + ref system
│ ├── selectors.py # 4-strategy selector resolver
│ └── actions.py # navigate, click, type, scroll, go_back, wait
├── dom/
│ ├── ref_map.py # ref ID ↔ element bidirectional mapping
│ └── compress.py # AX tree + MarkGrab → compressed context
├── llm/
│ ├── base.py # LLMProvider ABC
│ ├── provider.py # vLLM, Ollama, OpenAI-compatible
│ ├── prompt.py # System prompts (~400 tokens)
│ └── parse.py # 5-stage JSON fallback parser
├── agent/
│ ├── history.py # Sliding window history compression
│ ├── cache.py # Domain-based success pattern cache
│ └── loop_guard.py # Duplicate action detection
├── __main__.py # CLI (click)
└── mcp_server.py # FastMCP server (8 tools)所有设置均通过环境变量（BROWSEGRAB_* 前缀）进行：
# Browser
BROWSEGRAB_BROWSER_HEADLESS=true
BROWSEGRAB_BROWSER_TIMEOUT_MS=30000
# LLM (for agentic browse)
BROWSEGRAB_LLM_PROVIDER=vllm # vllm | ollama | openai
BROWSEGRAB_LLM_BASE_URL=http://localhost:8000/v1
BROWSEGRAB_LLM_MODEL=Qwen/Qwen3.5-32B-AWQ
# Agent
BROWSEGRAB_AGENT_MAX_STEPS=10
BROWSEGRAB_AGENT_ENABLE_CACHE=true库 | 角色 |
被动提取 (URL → Markdown) | |
被动捕获 (URL → 截图) | |
文档 OCR → 结构化 JSON | |
browsegrab | 主动自动化 (目标 → 浏览器动作 → 结果) |
git clone https://github.com/QuartzUnit/browsegrab.git
cd browsegrab
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
playwright install chromium
# Unit tests (no browser needed)
pytest tests/ -m "not e2e"
# Full suite including E2E
pytest tests/ -vQuartzUnit 生态系统的一部分 — 用于数据收集、提取、搜索和 AI 代理安全的可组合 Python 库。
This server cannot be deployed
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
E2LLM gives your AI eyes and hands in a real browser: structured perception (SiFR) plus action.
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
