Weavetab

dev.weavetab由 weavetab.dev 发布v2.5.0更新于 Oct 24, 2026

Open automation engine for AI agents. Control live browsers and desktop apps locally.

概览

AI 生成的概览

本地自动化引擎,让 AI 助手通过 Chrome DevTools 协议操控真实的 Chromium 浏览器和 Electron 桌面应用。

可以做什么
  • 读取与检查页面:语义地图、元素查找、抓取、截图、控制台与设计信息提取
  • 与页面交互:点击、输入、输入已存密钥、按键、指针悬停链、选择、填充、上传、滚动
  • 导航与环境管理:标签页、页面跳转、视口、模拟、设备检测
  • 执行自动化任务:批量操作、录制、模式学习、对话框、剪贴板、等待
  • 检查网络与存储:请求拦截、Cookie、存储、检查点、性能
  • 生成文档与画布输出:办公文档、PDF、画布与脚本求值
适用场景
适合需要助手操作真实浏览器会话或本地 Electron 应用(如 VS Code、Discord、Figma)而非无头脚本的场景,包括多步表单填写、网页抓取和重复性界面操作。
运行要求
以 npm 包形式通过 npx 在本地运行,需要 Node.js。需有正在运行且可通过本地 CDP 访问的 Chromium 系浏览器或已注册的 Electron 应用。可选配置保存在本地配置文件中,密钥保存在本地密钥文件中。仅支持桌面端。
安装前请注意
它能在真实应用和账号中点击、输入、上传、提交并修改数据,还能通过破解验证码绕过机器人检测。已存密钥虽在服务端解析,但仍保存在磁盘上。使用前应检查域名策略和基于角色的权限,审计日志会在本地记录工具活动。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Weavetab,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

[Weavetab]

The open automation engine for AI agents.
Control live browsers and desktop apps locally with instant execution.

[version] [license] [MCP] [Node] [tools]

Tool Reference  ·  Documentation  ·  Architecture  ·  Support  ·  Security


Weavetab is the open automation engine for AI agents. It connects models directly to live Chromium browsers and Electron desktop applications via native Chrome DevTools Protocol (CDP) sockets — no WebDriver binaries, no cloud relay, zero telemetry.

Actions execute directly over local CDP sockets without external driver overhead. Web pages are translated into agent-readable semantic maps with turn-by-turn diffing that reduces token usage by up to 95%. Built-in security enforces local domain policies, role-based access control, and client-side credential injection.

Built by Weavetab, architected by fy2ne.


Why not Playwright or Puppeteer?

The standard approach — Playwright over MCP — works. But it carries fundamental architectural costs that compound at scale.

Playwright / PuppeteerWeavetab
Protocol layerWebDriver BiDi or CDP via browser binaryDirect CDP WebSocket
Tool execution overhead50–300 ms (binary + IPC overhead)In-process (direct local socket)
Desktop app controlBrowser onlyChrome + any Electron app (Discord, VS Code, Figma…)
DOM representationFull HTML dump to LLMSemantic Map 3.0 with delta diffing
Token cost per map~2,000–8,000 tokens~80–400 tokens (95% reduction via delta)
CAPTCHAAPI service requiredZero-API via CDP mouse physics
Credential safetySecrets passed in plaintextBlind Injection — never in LLM context
Extension accessLimitedFull Chrome Extension API surface

Architecture

MCP Client (Claude / Cursor / Antigravity / Copilot / Windsurf)       |       |  JSON-RPC 2.0  (stdio or WebSocket 127.0.0.1:3000)       v+-------------------------------------------------------------+|                   Weavetab MCP Server                       ||                                                             ||  +-----------------+   +---------------------------------+  ||  | Security Layer  |-->|  Intelligence Engine            |  ||  | Rate · RBAC     |   |  Map 3.0 · Delta · Memory       |  ||  | Policy · Audit  |   |  Pruner · Framework Detector    |  ||  +-----------------+   +----------------+----------------+  ||                                         |                   ||                              +----------v----------------+  ||                              |  CDP Bridge               |  ||                              |  Ghost Cursor · Typing    |  ||                              |  App Router · Loop Guard  |  ||                              +----------+----------------+  |+-------------------------------------------------------------+                                          |  CDP WebSocket (127.0.0.1)              +---------------------------+-----------------------------+              v                           v                            v       Chrome / Edge               VS Code / Discord          Your Electron App       (any tab)                   (Electron apps)            (local dev)

No cloud. No external process. Both the CDP WebSocket connection and the optional MCP WebSocket daemon (--ws) are strictly bound to 127.0.0.1 with shared-secret authentication (~/.weavetab-system/ws-secret) and Origin/Host header verification.


Quick Start

bash
npx -y @weavetab/mcp

Add to your MCP client config:

json
{  "mcpServers": {    "weavetab": {      "command": "npx",      "args": ["-y", "@weavetab/mcp"]    }  }}
ClientConfig path
Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.json
Claude Codeclaude mcp add weavetab -- npx -y @weavetab/mcp
Cursor.cursor/mcp.json
Antigravity~/.gemini/antigravity/mcp/weavetab/
VS Code Copilot.vscode/mcp.json
Windsurf~/.codeium/windsurf/mcp_config.json

Core Technology

Semantic Map 3.0

The primary bottleneck in browser-based agents is DOM representation. Full HTML dumps are noisy, large, and structurally meaningless to language models. Weavetab's browser_map runs an in-browser CDP walker that produces a compact semantic map:

╔═ ACTIVE DIALOG: "Confirm Payment" ═╗  [w:3] button "Confirm"  [w:4] button "Cancel"
┌ "Pro Plan — $49/mo"  [w:12] button "Upgrade"   [w:13] button "View Details"  [w:14] input val:"[email protected]"  ph:"Email address"  FOCUSED
[w:20...w:38] 18 nav links: "Dashboard" ... "Sign out"

Key properties:

  • Ref IDs (w:N) are stable within a session and used by all interaction tools
  • Container binding — buttons and inputs are grouped under their parent card, row, or section header
  • Modal hoisting — open dialogs are isolated at the top so agents cannot miss them
  • Link collapsing — repeated nav/footer runs of 4+ links compress into a single token line
  • Semantic delta — on re-reads, only changed nodes are transmitted (~ modified, + added, − removed), cutting re-read cost by up to 95%

Ghost Cursor

Clicks are not dispatched as synthetic DOM events. They are delivered as a physical sequence of Input.dispatchMouseEvent CDP calls along a Bezier curve trajectory with randomized acceleration, natural jitter, and hold durations. Anti-bot fingerprinting that flags event-based automation does not trigger.

browser_pointer supports hover_chain for multi-level menu traversal in a single tool call:

json
{  "hover_chain": ["File", "Export As", "PNG"],  "click_final": true}

Blind Credential Injection

browser_type_secret resolves secrets server-side from ~/.weavetab/secrets.json. The resolved value is never included in the MCP response, never appears in DOM snapshots, and is permanently masked as [REDACTED] in all audit logs. The LLM context never sees the credential.

bash
weavetab secrets set GITHUB_TOKEN# Stored. Never echoed, never logged, never surfaced to the agent.

Electron & Desktop App Automation

Any tool accepts an optional app parameter that routes the command to a registered Electron process instead of a browser tab:

json
{ "app": "discord", "ref": "w:24", "text": "Hey, deploying now" }

Register apps in ~/.weavetab/config.json:

json
{  "electron": {    "discord":  "C:\\Users\\<user>\\AppData\\Local\\Discord\\Discord.exe",    "vscode":   "C:\\Users\\<user>\\AppData\\Local\\Programs\\Microsoft VS Code\\Code.exe",    "figma":    "C:\\Users\\<user>\\AppData\\Local\\Figma\\Figma.exe"  }}

Weavetab auto-attaches via CDP to the registered process. No code changes required in the target application.

Zero-API CAPTCHA Solving

browser_captcha solves Cloudflare Turnstile, reCAPTCHA v2/v3, GeeTest, and hCaptcha by orchestrating CDP mouse events that replicate human behavioral signatures — velocity curves, micro-pauses, scroll inertia — with no third-party API, no external service, and no API key required.


Tool Suite

41 tools across 9 categories. Full parameter reference: docs/tools/tools.md

CategoryTools
Vision & DOMbrowser_map browser_find browser_scrape browser_inspect browser_snapshot browser_screenshot browser_console browser_extract_design
Input & Interactionbrowser_click browser_type browser_type_secret browser_key browser_pointer browser_select browser_fill browser_upload browser_scroll
Navigation & Environmentbrowser_navigate browser_tabs browser_detect browser_viewport browser_emulate
Mission & Automationbrowser_burst browser_automation browser_recording browser_pattern_learn
Safety & Human Oversightbrowser_dialog browser_thoughts browser_clipboard browser_wait
Autonomous CAPTCHAbrowser_captcha
Network & Storagebrowser_network_intercept browser_storage browser_cookies browser_checkpoint browser_performance
Office Documentsbrowser_office
Canvas & Evalbrowser_eval browser_pdf browser_canvas browser_highlight

Security

  • Transport: Both CDP WebSocket and MCP WebSocket daemon (--ws) are strictly bound to 127.0.0.1 with 256-bit shared-secret Bearer/handshake authentication and Origin/Host validation. No listener on external interfaces.
  • Policy Engine: Per-domain allow / read-only / deny / audit rules under the top-level policies array in ~/.weavetab/config.json (blocks *.bank.* and paypal.com out of the box)
  • RBAC: Five roles — operator (default), viewer (least-privilege read-only), automation, system, admin — enforce tool-level permission gates
  • Plugin Trust & Manifests: 3-tier verification (@weavetab/* official, verified registry allowlist, and mandatory interactive confirmation + weavetab.json permission manifest inspection for unverified packages)
  • Blind Injection: Credentials resolved server-side, masked in all outputs and audit logs
  • Loop Breaker: Strike-based stuck-loop detector halts runaway autonomous sequences
  • Audit Log: All tool invocations, policy decisions, and errors written to ~/.weavetab-system/logs/mission_<timestamp>.log

Security vulnerabilities: [email protected] (do not use public issues).


CLI Reference

bash
weavetab                        # Start in stdio mode (default)weavetab --ws --port 3000       # WebSocket daemon mode (bound to 127.0.0.1)weavetab config                 # Interactive configuration wizardweavetab secrets set KEY_NAME   # Store a secret (never echoed)weavetab secrets list           # List stored secret keys (not values)weavetab plugin add <name>      # Install a verified/confirmed pluginweavetab plugin update <name>   # Interactively upgrade an installed pluginweavetab plugin list            # List installed plugins

Configuration file: ~/.weavetab/config.json

json
{  "browserType": "chromium",  "headless": false,  "extension": true,  "maxActionsPerMinute": 60,  "role": "operator",  "electron": {    "discord":     "...",    "vscode":      "...",    "antigravity": "..."  }}

Extensibility

Weavetab exposes a typed Plugin SDK for authoring custom MCP tools, HUD overlays, and tool lifecycle hooks:

bash
npx @weavetab/sdk init my-plugin

See docs/PLUGINS.md for architecture, manifest spec, and SDK API reference.


License

AGPL-3.0-only. Client connections over stdio or WebSocket do not extend copyleft obligations to your client application or models.

For commercial embedding, closed-source SaaS, or proprietary enterprise licensing, see COMMERCIAL.md or contact [email protected].

Sponsor on Ko-fi  ·  Discussions  ·  SUPPORT.md

来源:README.md,提交 129314c

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v2.5.0最新Oct 17, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分