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

sooryathejas/METATRON

AI-powered penetration testing assistant using local LLM on linux (Parrot OS) observed · 2026-08-28

github.com/sooryathejas/METATRON · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

48/100

  • Activity 76
  • Release rhythm 35
  • Longevity 10

Flags: no_releases young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 153
  • days_rel: n/a
  • days_push: 144
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

3616 stars · 729 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

METATRON is a CLI-based AI penetration testing assistant that runs a local LLM (via Ollama) entirely offline on Linux, primarily Parrot OS. It automates recon with tools like nmap, nikto, and whatweb, feeds results to the AI for vulnerability analysis and exploit suggestions, and stores scan history in MariaDB with PDF/HTML report export.

Use cases

  • run automated recon on a target IP or domain
  • analyze scan results with a local AI to identify vulnerabilities
  • get exploit suggestions and remediation recommendations offline
  • keep a persistent scan history in a database
  • export penetration test findings as PDF or HTML reports
  • look up CVEs and search the web without API keys

When to choose

  • you want an offline, no-API-key AI assistant for pentesting on Linux
  • you use Parrot OS or a similar security-focused distro and want integrated recon tooling
  • you need agentic AI that can request additional tool runs during analysis
  • you want scan history stored locally with report export

When to avoid

  • you need a cloud-based or team-collaborative pentest platform
  • you require guaranteed accuracy — LLM analysis can produce false positives and should not replace human judgment
  • you are not on Linux or cannot run Ollama with sufficient local hardware
  • you need compliance-certified scanning tools

Facets

cli-tool · maturity active

penetration-testing llm-inference agent-framework cli security search-engine security penetration-testing artificial-intelligence large-language-models developer-tools cli python offline-llm ollama recon-automation vulnerability-analysis mariadb parrot-os report-export local-ai reporting ai-agents command-line linux

1 source

Member repositories

RepositoryRoleHealth v2
sooryathejas/METATRONmain48

For agents

markdown · JSON · MCP: product_card(name="sooryathejas/METATRON")

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