mikita12/cognitive-browser

开发工具

本页由 AI 翻译，技术细节请以原文为准。查看原文

0 stars 0 forks 质量 81 趋势 14MIT

Repository Install

快速、高效的浏览器自动化MCP服务器。通过本地DeBERTa-v3 NLI解决常规网页交互，只有在歧义时才升级到LLM。

概览

认知浏览器使AI编码助手（Antigravity、Claude、Cursor）能够自主浏览网页，同时在DOM探索、填写输入、解析验证码（CAPTCHA）和点击多跳路线时进行操作。 - ⚡ 使用本地 ModernBERT / DeBERTa 交叉编码器模型在毫秒级（每个元素约 3.3ms 秒）内导航多跳网站。- 🧠 语义上将任意 JSON 表单词典（姓名、电子邮件、简历、简历、过滤器）绑定到 DOM 输入，无需硬编码 CSS 选择器。- 🚀 自动学习直接路径到页面和操作，实现近乎瞬间的 15 毫秒以下重复交互。- 🛡️ 限制访问仅限公共目的地，阻止云元数据 API（169.254.169.254），并防止 DNS 重新绑定。- 🍪 无缝导入本地 Firefox 配置文件或 cookie 文件中的认证会话，绕过 Cloudflare 和认证墙。- 🧩 由解耦的单责任模块构建（解析器、有效载荷、验证码、缓存、反射、编排器、浏览器）。

概述（AI 翻译）

零令牌自治浏览器代理和MCP服务器，由可插拔本地GPU交叉编码器/NLI路由（ReflexCore）、通用跨语言表单绑定（PayloadBinder）、隐匿游戏作者（BrowserEngine）和自我修复RouteCache）驱动。

*关于“零令牌”的注释：严格指认知浏览器MCP服务器和ReflexCore引擎，它们在GPU本地执行DOM候选排序、过滤和自主多跳导航，且具有0个LLM令牌。编排主机代理（如Ornith 1.5）仍消耗LLM令牌（平均：Arm A每集41,668个令牌，Arm B为85,332个）。

认知浏览器使AI编码助手（Antigravity、Claude Desktop、Cursor）能够在网页上导航、搜索动态SPA，并用浏览器服务器在DOM探索和执行动作时消耗的**0个LLM令牌*填充复杂的多字段表单。

精彩片段

⚡ 零令牌自主导航 & 51% 令牌减少： 在 GPU 上以毫秒级（~每个候选人 3.3ms 计;400+ DOM 元素在

完整技术规格请参见架构与工程指南（由 docs/architecture.d2 经 D2 编译而成）。

本页由 AI 翻译，技术细节请以原文为准。

README

以下为原文 README 节选，完整内容请查看原文。

Cognitive Browser

Zero-token autonomous browser agent & MCP server powered by pluggable local GPU Cross-Encoder / NLI routing (ReflexCore), universal cross-lingual form binding (PayloadBinder), Stealth Playwright (BrowserEngine), and self-healing RouteCache.

*Note on “Zero-Token”: Refers strictly to the Cognitive Browser MCP server and ReflexCore engine, which perform DOM candidate ranking, filtering, and autonomous multi-hop navigation locally on GPU with 0 LLM tokens. The orchestrating host agent (e.g. Ornith 1.5) still consumes LLM tokens (mean: 41,668 tokens/episode in Arm A vs 85,332 in Arm B).

Cognitive Browser enables AI coding assistants (Antigravity, Claude Desktop, Cursor) to navigate the web, search dynamic SPAs, and fill complex multi-field forms with 0 LLM tokens consumed by the browser server during DOM exploration and action execution.

Highlights

⚡ Zero-Token Autonomous Navigation & 51% Token Reduction: Navigates multi-hop websites on GPU in milliseconds (~3.3ms per candidate; 400+ DOM elements evaluated in <25ms), reducing overall agent LLM token consumption by 51.2% compared to standard Playwright MCP.
🔀 Hybrid Escalation Router: Executes confident navigation steps autonomously on GPU; when ambiguity is encountered, it seamlessly returns structured fallback candidates (partial_needs_fallback) for targeted host agent intervention via smart_action.
🔌 Pluggable Neural Models (Rerankers & NLI): Works out-of-the-box with any HuggingFace AutoModelForSequenceClassification — including multilingual Cross-Encoder Rerankers (mmarco-mMiniLMv2, bge-reranker-v2-m3, gte-reranker-modernbert-base) and NLI models (DeBERTa-v3, mDeBERTa-v3, ModernBERT-nli).
🧠 Dictionary-Free Cross-Lingual PayloadBinder: Partitions DOM controls by structural role (textbox, combobox, checkbox, upload_file) and binds arbitrary JSON payloads across languages (e.g., English keys to Polish forms or vice versa) with zero hardcoded synonym tables.
🚀 Self-Healing RouteCache: Learns deterministic shortcut routes in SQLite for near-instant repeat execution and automatically invalidates stale entries if a site’s DOM changes.
🛡️ SSRF & Security Guards: Restricts navigation to public destinations, blocks loopback/private networks and cloud metadata APIs (169.254.169.254), and mitigates DNS rebinding (per-request validation; resolve-then-connect TOCTOU remains).
🍪 Opt-In Cookie Sync & CAPTCHA Resolution: Can import authenticated sessions from local Firefox profiles (disabled by default; enabled via --enable-cookies flag) and integrates automated Turnstile / reCAPTCHA resolution.
🧩 Strongly-Typed Clean Architecture: Built with decoupled single-responsibility modules (models, parser, payload, captcha, cache, reflex, orchestrator, browser, security).

Architecture Overview

在 GitHub 查看完整 README

安装

This server does not publish a one-line install command.

Open the repository installation guide 新手？先看 mcpskill.org 教程 →

配置

{
  "mcpServers": {
    "cognitive-browser": {
      "command": "python3",
      "args": ["-m", "cognitive_browser.mcp_server"],
      "cwd": "/path/to/cognitive-browser",
      "env": {
        "COGNITIVE_BROWSER_MODEL": "cross-encoder/mmarco-mMiniLMv2-L12-H384-v1",
        "COGNITIVE_BROWSER_DEVICE": "cuda"
      }
    }
  }
}