Skip to content
KitploitKITPLOIT
OutilsExploitsBlog
Log in
Soumettre
OutilsExploitsBlog
Soumettre

Outils de Hacking, PenTest et Cybersécurité pour votre Arsenal de Sécurité !

Kitploit est un répertoire d'outils de hacking, de cybersécurité et de pentesting. Découvrez les dernières mises à jour des projets pour trouver des vulnérabilités, analyser des systèmes, automatiser les tests et renforcer votre sécurité.

FluxContactConfidentialité© 2026 Kitploit

Répertoire d'outils

Catégories

Voir toutes les catégories
Loading categories
Outils/GitHubGitHub/amd2g2zz/kunglao-agent
Sécurité AndroidAnalyse StatiqueAnalyse Dynamique (Sandboxing)Analyse des VulnérabilitésPentesting d'Applications MobilesRétro-ingénierieSécurité WebAnalyse de MalwareAnalyse de BinairesRétro-Ingénierie Assistée par IAAnalyse de Micrologiciel
8026187il y a 13 joursVérifié par Kitploit
Partager
GitHubamd2g2zz/kunglao-agent

kunglao-agent

L'agent expert en rétro-ingénierie : planifie son propre parcours d'analyse, déduit chaque fait à partir de preuves brutes et converge sous des portes de vérification mécaniques — firmware, protocoles, web/JS, contrôle des risques, binaires.

Voir le dépôtSite web
Contenu non disponible dans la langue demandée. Affichage de la version anglaise.

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.

Télécharger l’outil

Populaires

Voir tout →

Découvrez les outils les plus utilisés par notre communauté.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 La boîte à outils OSINT ultime : graphe d'enquête, notation de confiance, familles d'alias, carte, chronologie et rapports. 49 modules, plus de 400 sites, aucune clé API requise.

    540
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    # Application d'exécution en un clic GhostLock (CVE-2026-43499)

    476
  • 3

    ARTEX

    baarai/artex

    Plateforme autonome de tests d'intrusion multi-agents basée sur des LLM, avec agents planificateur/ouvrier, graphes d'actifs et d'exploration, enregistrement du trafic MITM et retest des vulnérabilités.

    373
  • 4

    redforge

    cybersecurity91/redforge

    Boîte à outils red team côté navigateur avec 102 outils hors ligne pour la reconnaissance, la génération de payloads, les attaques par identifiants, la cryptographie, l'encodage et le reporting d'engagement.

    322
  • 5

    estorides

    grisuno/estorides

    Agrège plus de 99 sources OSINT gratuites en parallèle, résout les entités dans un graphe de connaissances et exporte en STIX 2.1, MISP ou GraphML avec une analyse assistée par LLM.

    278
  • 6

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    Le système d'action pour la cybersécurité native IA—où l'intention devient une exécution gouvernée, les preuves deviennent une mémoire opérationnelle, et chaque opération améliore la suivante.

    251

Explorer tous les outils

Parcourez notre collection d'outils

Voir tous les outils →