Skip to content
KitploitKITPLOIT
HerramientasExploitsBlog
Log in
Enviar
HerramientasExploitsBlog
Enviar

¡Herramientas de Hacking, PenTest y Ciberseguridad para tu Arsenal de Seguridad!

Kitploit es un directorio de herramientas de hacking, ciberseguridad y pentesting. Descubre las últimas actualizaciones de proyectos para encontrar vulnerabilidades, analizar sistemas, automatizar pruebas y fortalecer tu seguridad.

FeedsContactoPrivacidad© 2026 Kitploit

Directorio de Herramientas

Categorías

Ver todas las categorías
Loading categories
kunglao-agent — El agente experto en ingeniería inversa: planifica su propia ruta de análisis, deriva cada hecho a partir de evidencia sin procesar y converge bajo compuertas de verificación mecánica — firmware, protocolos, web/JS, control de riesgos, binarios. | Kitploit
Herramientas/GitHubGitHub/amd2g2zz/kunglao-agent
Seguridad AndroidAnálisis EstáticoAnálisis Dinámico (Sandboxing)Análisis de VulnerabilidadesPentesting de Apps MóvilesIngeniería InversaSeguridad WebAnálisis de MalwareAnálisis de BinariosReversing Asistido por IAAnálisis de Firmware
8026187hace 13 díasRevisado por Kitploit
Compartir
GitHubamd2g2zz/kunglao-agent

kunglao-agent

El agente experto en ingeniería inversa: planifica su propia ruta de análisis, deriva cada hecho a partir de evidencia sin procesar y converge bajo compuertas de verificación mecánica — firmware, protocolos, web/JS, control de riesgos, binarios.

Ver RepositorioSitio web
Contenido no disponible en el idioma solicitado. Mostrando versión en inglés.

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.

Descargar herramienta

Más Populares

Ver todos →

Descubre las herramientas más usadas por nuestra comunidad.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 El kit de herramientas OSINT definitivo: grafo de investigación, puntuación de confianza, familias de alias, mapa, línea de tiempo e informes. 49 módulos, más de 400 sitios, sin necesidad de claves API.

    540
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    # Aplicación de Ejecución con un Solo Toque GhostLock (CVE-2026-43499)

    476
  • 3

    ARTEX

    baarai/artex

    Plataforma de pruebas de penetración autónoma multiagente basada en LLM con agentes planificadores/trabajadores, grafos de activos y de exploración, registro de tráfico MITM y reevaluación de vulnerabilidades.

    373
  • 4

    redforge

    cybersecurity91/redforge

    Kit de herramientas de red team del lado del navegador con 102 herramientas offline para reconocimiento, generación de payloads, ataques de credenciales, criptografía, codificación y elaboración de informes de compromiso.

    322
  • 5

    estorides

    grisuno/estorides

    Agrega más de 99 fuentes OSINT gratuitas en paralelo, resuelve entidades en un grafo de conocimiento y exporta STIX 2.1, MISP o GraphML con análisis asistido por LLM.

    278
  • 6

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    El sistema de acción para la ciberseguridad nativa de IA—donde la intención se convierte en ejecución gobernada, la evidencia se convierte en memoria operativa y cada operación mejora la siguiente.

    251

Explora todas las herramientas

Explora nuestra colección de herramientas

Ver todas las herramientas →