# zakirkun/guardian-cli

Guardian is a production-ready AI-powered penetration testing automation CLI tool that leverages Google Gemini and LangChain to orchestrate intelligent, step-by-step penetration testing workflows while maintaining ethical hacking standards.

Repository: https://github.com/zakirkun/guardian-cli
Canonical: https://ross.abutalabs.com/products/guardian-cli
Language: Python
License: NOASSERTION
License Family: other
Topics: automation, gemini-ai, generative-ai, pentest-tool
Last push: 2026-06-27T19:20:49+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 89, release rhythm 72, longevity 18
- inputs: {"age_days": 254, "days_push": 67, "days_rel": 187, "gap_med": 23, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1853, forks 367 (observed 2026-08-28T04:05:44.567833+00:00)

## What it is
Guardian is a Python CLI tool that automates penetration testing workflows using LLM providers (OpenAI, Claude, Gemini, Ollama, and others) orchestrated via LangChain. It combines multi-agent AI planning, debate-based false-positive triage, and a RAG knowledge base of CVE/CWE/MITRE data with traditional security tooling for authorized security assessments.

## Use cases
- automate penetration testing workflows with AI
- run authorized security assessments from the command line
- triage and filter false-positive vulnerability findings with multi-agent debate
- ground vulnerability references in CVE/CWE/MITRE ATT&CK data
- orchestrate pentest tools with an LLM planner
- run local-model pentest automation with Ollama

## When to choose
- you are a security professional running authorized pentests and want LLM-assisted orchestration
- you want adaptive, multi-agent AI triage of findings with evidence capture
- you need provider flexibility including local models via Ollama

## When to avoid
- you need a fully hands-off scanner without human oversight or authorization to test targets
- you require a license-guaranteed open-source tool (license is non-standard despite MIT badge)
- you need a lightweight scanner without LLM API costs or dependencies

## Facets
- artifact type: cli-tool
- maturity: active
- function: penetration-testing, agent-framework, llm-inference, rag, security, workflow-automation, cli
- domain: security, penetration-testing, artificial-intelligence, developer-tools
- platform: python, cli, cross-platform
- tags: pentest, gemini, langchain, multi-agent, llm-orchestration, ethical-hacking, vulnerability-assessment, ai-automation, ai-agents, command-line, linux, macos

## Member repositories
- zakirkun/guardian-cli (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:44.567833+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:16:51.362643+00:00, confidence not recorded.
  - readme: https://github.com/zakirkun/guardian-cli (fetched 2026-08-28T04:05:44.567833+00:00, sha 79718aa20eb0)
- Data as of 2026-08-30T08:39:29.467469+00:00.