English Français العربية

io.github.perzianhq/mantis

السجل الرسمي البحث والويب

The web as short, numbered text for AI agents: a lean browser interface over Playwright.

الشيفرة المصدرية التوثيق

التثبيت

أضف هذا إلى إعدادات MCP في عميلك (Claude Desktop: claude_desktop_config.json، وCursor: ‏.cursor/mcp.json، ويستخدم VS Code وغيره الصيغة نفسها «mcpServers»).

NPM package mantis-browser
Claude Code 
claude mcp add mantis -- npx -y mantis-browser@0.1.10
إعداد JSON (Claude Desktop وCursor وVS Code) 
{
    "mcpServers": {
        "mantis": {
            "command": "npx",
            "args": [
                "-y",
                "mantis-browser@0.1.10"
            ]
        }
    }
}

التوثيق

مأخوذ من ملف README للمشروع على GitHub ويُحدَّث أسبوعيًا. تفتح الروابط على GitHub.

المحتويات
  1. How it works
  2. What the agent sees
  3. Results
  4. Learn more
  5. License

Lets AI agents browse the web as short, numbered text instead of screenshots.

perzian.dev/mantis · by Perzian

It works with Claude Code, Codex, Cursor or your own agent as an MCP server. Install in two commands.

How it works

What the agent sees

Results

Same tasks, same pass criteria, three ways to browse. Mantis vs the accessibility tree (Playwright MCP) vs screenshots.

Long multi-step workflows (long-local-v1: 16 local tasks with in-page hazards, 3 runs per approach, code-graded). Score is out of 48; time is mean agent execution per run.

ModelMantisAccessibility treeScreenshots
gpt-6-lunaCorrect48/4848/4842/48
Time103s132s163s
Input tokens17.3M28.0M31.0M
Tool calls119016852774
claude-haiku-5-5Correct48/4848/4848/48
Time42s59s64s
Input tokens12.1M18.7M27.1M
Tool calls150118272876

Real sites (live-v1 v1.7: 30 tasks, 3 runs per approach, judged blind). Success out of 90:

ModelMantisAccessibility treeScreenshots
gpt-6-luna899085
claude-haiku-5-5878689

Net: Accuracy is on par with the tree (within 1 run of 90 on real sites, equal on long workflows). The roughly 30% saving in tokens and calls was measured on long workflows that run on local fixtures, not live sites; on real-site tasks, which are shorter, the difference is smaller. Accuracy claims cover read/navigate tasks on public sites with Luna and Haiku. The screenshot baseline is our own minimal tool, not a product's.

Where Mantis is better
  • Long workflows. Same accuracy as the tree, with 22–29% less time, 35–38% fewer input tokens and 18–29% fewer tool calls, because each step returns only what changed.
  • Versus screenshots. Fewer tokens and calls everywhere; Luna also missed 6 of 48 where Mantis and the tree did not.
  • Short tasks. Roughly a tie with the tree. The edge grows with task length.

Method and caveats: bench/RESULTS.md.

Learn more

License

MIT

الأسئلة الشائعة

ما هو io.github.perzianhq/mantis؟

The web as short, numbered text for AI agents: a lean browser interface over Playwright.

كيف أثبّت io.github.perzianhq/mantis؟

يعمل على جهازك. في Claude Code: claude mcp add mantis -- npx -y mantis-browser@0.1.10. وفي العملاء الآخرين، الصق إعداد JSON من هذه الصفحة في إعدادات MCP الخاصة بهم.

هل يحتاج io.github.perzianhq/mantis إلى مفتاح API؟

لا يذكر إدراجه في السجل أي مفتاح أو سر إلزامي. قد تتطلب بعض الميزات حسابًا لدى الخدمة التي يتصل بها.

هل io.github.perzianhq/mantis مفتوح المصدر؟

نعم. شيفرته متاحة على GitHub بترخيص MIT.

من يصون io.github.perzianhq/mantis؟

ينشره perzianhq. يدرجه AI.tn لكنه لا يصونه ولا يوصي به.

من سجل MCP الرسمي. الإدراج ليس توصية: راجع شيفرة الخادم وصلاحياته قبل منحه الوصول إلى بياناتك.