Skip to content
KitploitKITPLOIT
도구익스플로잇블로그
Log in
제출
도구익스플로잇블로그
제출

해킹, 침투 테스트 및 사이버 보안 도구를 당신의 보안 무기고에!

Kitploit은 해킹, 사이버 보안 및 침투 테스트 도구 디렉토리입니다. 최신 프로젝트 업데이트를 발견하여 취약점을 찾고, 시스템을 분석하고, 테스트를 자동화하고, 보안을 강화하세요.

피드문의개인정보© 2026 Kitploit

도구 디렉토리

카테고리

모든 카테고리 보기
Loading categories
kunglao-agent — 리버스 엔지니어링 전문 에이전트: 자체 분석 경로를 계획하고, 모든 사실을 원시 증거로부터 도출하며, 기계적 검증 게이트 아래에서 수렴합니다 — 펌웨어, 프로토콜, 웹/JS, 리스크 컨트롤, 바이너리. | Kitploit
도구/GitHubGitHub/amd2g2zz/kunglao-agent
Android SecurityStatic AnalysisDynamic Analysis (Sandboxing)Vulnerability AnalysisMobile App PentestingReverse EngineeringWeb SecurityMalware AnalysisBinary AnalysisAI-Assisted ReversingFirmware Analysis
802618713일 전Kitploit 검토 완료
공유
GitHubamd2g2zz/kunglao-agent

kunglao-agent

리버스 엔지니어링 전문 에이전트: 자체 분석 경로를 계획하고, 모든 사실을 원시 증거로부터 도출하며, 기계적 검증 게이트 아래에서 수렴합니다 — 펌웨어, 프로토콜, 웹/JS, 리스크 컨트롤, 바이너리.

저장소 보기웹사이트
요청한 언어로 콘텐츠를 사용할 수 없습니다. 영어 버전을 표시합니다.

kunglao-agent

An autonomous reverse-engineering agent that runs for hours unattended, verifies every conclusion independently, and converges only when every answer survives a mechanical oracle verdict.

release release-check python runtime license

🧠 plans its own route · 🔬 every claim machine-checked · ⚖️ blind verification on everything · 📈 the loop measures itself

📖 Introduction · 🖥️ Showcase · ✨ Core technology · 🧠 kunglao × Claude Code · 🎛️ Online RL: the loop gets better while it works · 📋 Requirements · Quick start · Subcommands · What a run looks like · 📖 Stating the task · 🧰 The run you watch · 📚 Case studies · 🧪 Evaluation and measured results · 🏗️ Architecture · Bring your own environment · MCP servers · 🗓️ Roadmap · ❓ FAQ · 🔐 Safety · 🧪 Development · 📝 License

English · 简体中文

[!WARNING] v0.1.6 is the last Claude Code-native release line. The next milestone (v0.2) migrates the runtime wholesale to the PI Agent base — same loop, same ledgers, new engine substrate. See the roadmap.


📖 Introduction

You point kunglao-agent at a target and state the questions; it plans the route, dispatches specialist workers, verifies every conclusion independently, and stops only when each answer is settled by a mechanical check instead of a model's say-so.

The target spectrum is the full one — Windows/Linux native binaries, Android APKs (including native .so layers), web/JS, protocol recovery, firmware — static-first by design, driving whichever execution channel your environment already has (VMware, ssh, docker, adb, or none at all for static-only work).

It runs inside Claude Code as a plugin: Claude Code is the conversation surface; the product is the loop and the fact base it produces.

[!NOTE] Every number the loop reports — win rates, posteriors, budgets — traces to a row on an append-only ledger. Nothing is self-declared.


🖥️ Showcase

The orchestrator at work — a convergence decision, a budgeted worker dispatch with live facts landing, and a blind red-team verdict promoting a claim to PROVEN; the statusline HUD keeps the whole engagement readable at a glance:

kunglao-agent orchestrator session: convergence check, worker dispatch, blind red-team verification, statusline HUD

The loop measuring itself — the round strategy composed from settlements, the discounted-Thompson posterior store with censored-outcome tiebreaking, the discovery layer admitting a genuinely novel arm (and refusing a renamed retry), and the win-rate curve:

kunglao-agent learning faces: round strategy, posterior store, expansion receipt, win-rate curve


✨ Core technology

kunglao-agent is an act-level RL controller around Claude Code: Claude Code reasons inside each act; kunglao decides the next act, verifies it, prices it, learns from it. Deep design: docs/design/.

  • Mechanical oracle. The completion criterion derives from your task statement as runnable checks (byte-exact replay, held-out probes). Reward is priced in oracle verdicts — lying about progress earns nothing.
  • Blind verification. An independent verifier re-derives every claim without seeing the maker's reasoning; worker self-sign-off caps at STAMP, never PROVEN. Facts cite artifacts (sha256) and carry reproduce: commands.
  • The loop learns, the model stays frozen. Every act lands on an append-only ledger; a Thompson-sampling policy reorders method families by measured cost-adjusted success per feature-keyed state.
  • Unattended, resumable. Hours-long runs, dead workers replaced, full state on disk, every reported number traces to a ledger row.

🧠 kunglao × Claude Code

Claude Code is the engine; kunglao is the gearbox, dashboard, and flight computer — next act, verification, budget, and where experience goes.

bare Claude Code+ kunglao
Next stepimprovised in-sessionlearned act-level policy, posteriors persist across tasks
Verificationself-reportmechanical oracle + blind red-team
Durationone session, human watchinghours unattended, resume from disk
Experienceevaporates at session endledger → posteriors → sharper opening bet

The controller picks each act, Claude Code executes it, the ledger remembers

Honest boundary: for a simple single-session task, bare Claude Code wins — the evaluation table says so. kunglao pays off on long horizons, verification discipline, and cross-task compounding.


🎛️ Online RL: the loop gets better while it works

The first task of a new kind pays full price: the loop tries a method, watches it fail, tries another. But every attempt is written down — and the next task of the same kind opens from those notes, not from zero.

One task pays full price; the loop remembers; the second runs cheaper

That is the whole idea of online reinforcement learning here: the loop updates itself between acts, on the job — no training dataset, no model retraining, no offline phase. Each task's experience is banked before the next decision is made.

What the loop actually learns

1. The right first move, per kind of target. A plain script and a hardened app should not open the same way. The loop keeps separate notes per kind of target — what the target looks like decides which playbook applies.

Two targets route to two different playbooks

2. Which methods are dead. A method that keeps failing gets benched — it stops eating budget (but is never deleted; if the target changes, it can come back). And when nothing works, the loop tries to invent a way in: a discovery act proposes a genuinely new approach, checked against the failed tries — the same idea renamed is refused.

도구 다운로드

인기

모두 보기 →

커뮤니티에서 가장 많이 사용되는 도구를 찾아보세요.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 궁극의 OSINT 툴킷: 조사 그래프, 신뢰도 점수 산정, 별칭 패밀리, 지도, 타임라인 및 보고서. 49개 모듈, 400개 이상 사이트, API 키 불필요.

    540
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    # GhostLock 원탭 실행 앱 (CVE-2026-43499)

    476
  • 3

    ARTEX

    baarai/artex

    LLM 멀티 에이전트 자율 침투 테스트 플랫폼으로, 플래너/워커 에이전트, 자산 및 탐색 그래프, MITM 트래픽 기록, 취약점 재테스트 기능을 제공합니다.

    373
  • 4

    redforge

    cybersecurity91/redforge

    브라우저 측 레드 팀 툴킷으로, 정찰, 페이로드 생성, 자격 증명 공격, 암호화, 인코딩 및 참여 보고를 위한 102개의 오프라인 도구를 제공합니다.

    322
  • 5

    estorides

    grisuno/estorides

    99개 이상의 무료 OSINT 소스를 병렬로 집계하고, 엔티티를 지식 그래프로 해석하며, LLM 지원 분석과 함께 STIX 2.1, MISP 또는 GraphML로 내보냅니다.

    278
  • 6

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    AI 네이티브 사이버보안을 위한 행동 체계—의도가 통제된 실행이 되고, 증거가 운영 메모리가 되며, 모든 운영이 다음 운영을 개선하는 곳.

    251

모든 도구 탐색

도구 컬렉션을 둘러보세요

모든 도구 보기 →