Ross ROSS = Recommend OSS · open-source software intelligence for agents

zakirkun/deep-eye

Deep Eye orchestrates multiple AI providers (OpenAI, Claude, Grok, Gemini, OLLAMA, Groq, Mistral, OpenRouter, LiteLLM, LM Studio) for intelligent payload generation, scans targets for 45+ vulnerability types, and produces professional reports with compliance mapping. observed · 2026-08-28

github.com/zakirkun/deep-eye · Python · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

68/100

  • Activity 99
  • Release rhythm 54
  • Longevity 23

Flags: no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 322
  • days_rel: 98
  • days_push: 7
  • n_releases_24m: 1

Full methodology

Adoption not part of the score

2219 stars · 406 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Deep Eye is an AI-driven penetration testing CLI that orchestrates multiple LLM providers (OpenAI, Claude, Gemini, OLLAMA, Groq, and others) to generate context-aware payloads and scan web targets for 50+ vulnerability types. It produces professional reports with compliance mapping (PCI-DSS, SOC2, ISO 27001), false-positive triage, and export to formats like HTML, PDF, SARIF, and JSON.

Use cases

  • scan a web app for sql injection and xss vulnerabilities
  • generate ai-powered payloads for penetration testing
  • automate bug bounty report writing
  • map security findings to pci-dss and iso 27001 compliance
  • run vulnerability scans with multiple llm provider failover
  • retest a target and diff against a previous scan baseline
  • seed a crawl from an openapi swagger spec

When to choose

  • you want LLM-assisted payload generation and false-positive triage in a single pentest tool
  • you need compliance-mapped, exportable vulnerability reports
  • you want flexible AI provider support including local models via OLLAMA
  • you run bug bounty work and want HackerOne-style report drafts

When to avoid

  • you need a fully passive or compliance-audit-only scanner without AI dependencies
  • you cannot provide any AI provider API key and have no local model
  • you require a license-audited tool - the license is listed as NOASSERTION despite an MIT badge
  • you need a mature enterprise scanner with long-term vendor support

Facets

cli-tool · maturity active

penetration-testing vulnerability-scanning llm-inference agent-framework security security penetration-testing artificial-intelligence developer-tools python windows cli ai-driven-pentesting payload-generation bug-bounty compliance-mapping multi-provider-llm web-security-scanner nuclei-templates playwright reporting linux macos

1 source

Member repositories

RepositoryRoleHealth v2
zakirkun/deep-eyemain68

For agents

markdown · JSON · MCP: product_card(name="zakirkun/deep-eye")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem