# SanMuzZzZz/LuaN1aoAgent

LuaN1aoAgent is a fully autonomous AI-driven penetration testing agent powered by graph-based cognitive reasoning. Developed by the Intelligent Offense & Defense Research Group, led by Professor Lu Hui and Tian Zhihong at Fang Class, Guangzhou University.

Repository: https://github.com/SanMuzZzZz/LuaN1aoAgent
Canonical: https://ross.abutalabs.com/products/luan1aoagent
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Topics: pentest, agents, cybersecurity, llm, ai, ai-agents, ai-security-tool, autonomous-agents, large-language-models, multi-agent-systems, penetration-testing, penetration-testing-tools, security-automation, security-tools, deepseek, plan-execute-reflect, causal-graphs, pi-sdk, graph, graph-agent
Last push: 2026-08-24T10:36:20+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 93, longevity 19
- inputs: {"age_days": 272, "days_push": 9, "days_rel": 44, "gap_med": 0, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1276, forks 183 (observed 2026-08-28T04:04:13.013797+00:00)

## What it is
LuaN1aoAgent is an autonomous AI-driven penetration testing agent built in TypeScript on the Pi SDK, using graph-based cognitive reasoning with a Planner-Executor-Observer architecture. It targets authorized security research, keeping every conclusion traceable to persisted events, artifacts, and graph evidence.

## Use cases
- automate penetration testing with an AI agent
- run autonomous security assessments on authorized targets
- build multi-agent pentest workflows with graph reasoning
- trace security findings back to evidence and artifacts
- orchestrate LLM-driven offensive security tooling
- plan and execute scoped pentest tasks automatically

## When to choose
- you need an autonomous, evidence-traceable pentest agent rather than a manual scanner
- you want graph-based cognitive planning for security tasks
- you're doing authorized security research with LLM-driven tooling
- you prefer a TypeScript/Node.js agent runtime

## When to avoid
- you need a stable, benchmark-validated tool - v2 is a rewrite with unverified benchmarks
- you need a passive vulnerability scanner or compliance checker
- unauthorized testing - the tool is designed for authorized research only
- you need a Python-based v1-compatible workflow

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, penetration-testing, llm-inference, security, workflow-automation
- domain: penetration-testing, security, large-language-models
- platform: cli, cross-platform
- tags: autonomous-agents, multi-agent-systems, graph-based-reasoning, plan-execute-reflect, pentest-automation, typescript, pi-sdk, evidence-tracing, ai-agents, automation, nodejs

## Member repositories
- SanMuzZzZz/LuaN1aoAgent (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:13.013797+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 2026-08-30T05:02:54.683627+00:00, confidence not recorded.
  - readme: https://github.com/SanMuzZzZz/LuaN1aoAgent (fetched 2026-08-28T04:04:13.013797+00:00, sha a2cc5af7d0bd)
- Data as of 2026-08-30T08:39:29.467469+00:00.