AI TOOLS/AI 工具·CHAT-AGENT

browser39

alejandroqh/browser39

中文简介生成中A headless browser for AI agents that fetches modern web pages, runs JavaScript, manages sessions, and returns token-efficient Markdown.

打开仓库Open repository

怎么装：Install: npm install @aquintanar/browser39

02 / 现在的位置02 / Why now

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

历史不足Not enough history

只有 1 个快照，还不足以计算增长Only 1 snapshots so far — not enough to compute growth

讨论DISCUSSION

暂无None

还没有采集到外部讨论No external discussion collected yet

状态STATUS

长期未更新Not updated

03 / 它能帮你做什么03 / What it helps you do

它能帮你做成什么What it helps you do

中文能力说明生成中Chinese capability copy is being generated

05 / 安装05 / Install

怎么装How to install

NPM

$

Node 用户的安装方式。The install route for Node users.

CARGO

$

README 里给出的安装方式。The installation method given in the README.

两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.

06 / 限制与风险06 / Limits and risk

限制与风险Limits and risk

风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

存在风险Risk found

01需要 API KeyREQUIRES API KEY: 是Yes
02需要本地环境NEEDS LOCAL RUNTIME: 未在文档中发现Not found in the docs
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 需要 API KeyNeeds an API key

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/alejandroqh/browser39
原始数据哈希Raw data hash: 4fd4caac34f1d58b4457d51b1eba8f9e
解析时间Parsed at: 2026-10-03T11:06:29.602Z
最后一次验证Last verified: 2026-10-03T10:31:51.693Z
增长测量时间Growth measured: 2026-10-03T11:08:26.014Z
发现查询Discovery queries: focus:token:code:token-usage
分类来源Category source: rules
焦点Focus: token (6)

静态扫描STATIC SCAN

01执行远程脚本Runs a remote scriptreadme

curl -fsSL https://raw.githubusercontent.com/alejandroqh/marketplace/main/h39.sh | bash

02控制浏览器Controls a browserreadme

- **Single binary.** No Chrome, no Puppeteer. ~52MB. macOS, Linux, Windows.

这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "tree: .claude-plugin/"
    },
    {
      "agent": "claude-desktop",
      "evidence": "readme: …detected: **Claude Code**, **Claude Desktop**, **Codex**, **OpenCode**, *…"
    },
    {
      "agent": "opencode",
      "evidence": "readme: …laude Desktop**, **Codex**, **OpenCode**, **OpenClaw**. ```sh curl…"
    }
  ],
  "apiKey": "\"Authorization\" value_env = \"GITHUB_TOKEN\" value_prefix = \"Bearer \" domains = [\"a",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 2,
      "dev-tools": 1,
      "indie-web": 0,
      "skill-agent": 7,
      "productivity": 0
    },
    "primary": "ai-tools",
    "secondary": "chat-agent"
  },
  "localRuntime": null,
  "skillMdTotal": 0,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 3,
    "media": 0,
    "design": 1,
    "browser": 5,
    "devtool": 2,
    "security": 0,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "Claude Code plugin manifest",
      "weight": 0.7
    },
    {
      "signal": ".mcp.json (configures servers it uses)",
      "weight": 0.3
    },
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme"
  ],
  "skillMdFetched": 0
}