deep-eye - Deep Eye orchestrates multiple AI providers (OpenA

项目说明

<p align="center">
<a href=" target="_blank" rel="noopener noreferrer"><img src=" alt="zakirkun%2Fdeep-eye | Trendshift" width="250" height="55"/></a>
<br />
<img src="./assets/logo.png" height="300">
</p>

<h1 align="center">Deep Eye</h1>

<p align="center">
Ad AI-Dri Testing Tool
</p>

<p align="center">
<img src=" alt="">
<img src=" alt="Python">
<img src=" alt="License">
<img src=" alt="代码 Name">
</p>

---

Deep Eye orchestrates multiple AI pro (OpenAI, Claude, Grok, Gemini, OLLAMA, Groq, Mistral, OpenRouter, OrcaRouter, LiteLLM, LM Studio) for intelligent payload generation, scans targets for 50+ checks, and produces professional reports with compliance mapping, dedupe, and retest workflows.

Features

Requirements

Installation

Windows:

Linux/Mac:

Manual:

First launch without config runs the interacti.

Browser automation (optional):

Usage

Basic Scan

With Configuration File

/ Multi-format

Natural-language scope

Scan Diffing

Retest only new findings

CLI Reference

| Flag | Description |
|------|-------------|
| -u, --url | Target URL (o config) |
| -c, --config | Config file path (default: config/config.yaml) |
| - | output |
| -- | Show |
| --no-banner | Disable ASCII banner |
| --formats | Comma-separated: html,pdf,json,junit,csv,xlsx,sarif |
| --diff | Diff two scan JSON files (BASELINE CURRENT) |
| --diff-output | Diff report path |
| --diff-format | html, json, or csv |
| --retest-new | After scan, keep only findings new JSON |
| --scope-nl | Natural-language scope string |
| --setup | Run interacti setup wizard and exit |
| --setup-force | With --setup, o existing config without extra prompt |

Configuration

All behavior is controlled via config/config.yaml. See docs/CONFIGURATION.md and config/config.example.yaml.

AI Pro

Supported: openai, claude, grok, ollama, gemini, openrouter, orcarouter, requesty, mistral, groq, lmstudio, litellm, n

Scanner Settings

Checks

OpenAPI / AI pipeline (optional)

Project structure

Documentation

| Doc | Content |
|-----|---------|
| docs/QUICKSTART.md | Install + first scan |
| docs/CONFIGURATION.md | Full YAML reference |
| docs/MODULES.md | Module catalog |
| docs/ARCHITECTURE.md | Layers + contracts |
| docs/SCAN_FLOW.md | Phase pipeline |
| docs/SKILLS.md | Agent skills (pentest / bounty / red / blue / CTF) |
| CLAUDE.md | Agent/de |
| AGENTS.md | Hierarchical agent map |

Testing

Scripts

Sponsors

<p align="center">
<a href=" target="_blank" rel="noopener noreferrer">
<img src="./assets/swiftproxy_banner.png" alt="Swiftproxy" width="100%">
</a>
</p>

<p align="center">
<a href=" provides 90M+ clean residential IPs across 220+ locations, supporting HTTP(S)/SOCKS5, IP rotation, sticky sessions, and precise location targeting. It helps browser automation and AI-powered workflows access websites reliably from different locations — suitable for web scraping, automation, research, and location-based testing. Residential proxies from $0.7/GB.
<br />
Free testing a. Use 代码 <代码>PROXY90</代码> for 10% off.
</p>

Legal Disclaimer

Deep Eye is for authorized security testing only.

License

MIT License. See LICENSE.

Links

项目信息

开发语言：Python

Star 数：2331

技术要点

该项目属于黑客技术方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕Deep Eye orchestrates multiple AI pro (OpenAI, Claude, Grok, Gemini, OLLAMA, Groq, Mistral, OpenRouter, LiteLLM, LM Studio) for intelligent payload generation, scans targets for 45+ types, and produces professional reports with compliance mapping.展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。