Skip to content
KitploitKITPLOIT
ToolsExploitsBlog
Log in
Submit
ToolsExploitsBlog
Submit

Hacking, PenTest, and Cybersecurity Tools for Your Security Arsenal!

Kitploit is a directory of hacking, cybersecurity, and pentesting tools. Discover the latest project updates to find vulnerabilities, analyze systems, automate testing, and strengthen your security.

FeedsContactPrivacy© 2026 Kitploit

Tool Directory

Categories

View all categories
Loading categories
mythic_ornn — LLM-driven generator for Mythic Agents, Payload-Type and C2 Profiles. | Kitploit
Tools/GitHubGitHub/n0qword/mythic_ornn
Penetration Testing FrameworksExploit FrameworksCommand and ControlRed TeamingPayload DevelopmentAI Security
GitHubn0qword/mythic_ornn

mythic_ornn

LLM-driven generator for Mythic Agents, Payload-Type and C2 Profiles.

View Repository
563972 months agoReviewed by Kitploit
Share

Mythic Ornn

Ornn fanart

LLM-driven generator for Mythic Agents, Payload-Type and C2 Profiles.

Mythic agents are tedious to write by hand: every one re-implements the same wire protocol, payload-type scaffolding, and C2 plumbing. Mythic Ornn skips the boilerplate by turning the official Mythic developer docs into the retrieval layer of a generation pipeline. An LLM consults a local, pruned copy of those docs and emits agents that match the documented message format out of the box.

The pipeline works in two modes, sharing the same docs and the same rules:

  • Prompt mode — template/AGENT.md turns any coding agent into a Mythic developer. You describe an agent, it reads the docs, and it scaffolds or extends a project. This is the interactive, in-editor workflow.
  • Build mode — ornn-agent/ is a Mythic payload type that generates other agents from the Mythic UI. Describe an agent, hit build, and the container (LLM + bundled docs + a Python template) returns a runnable payload. It's a payload type that produces payload types.

Structure

  • mythic-doc/ — pruned copy of the official Mythic docs; the context fed to the model during generation.
  • template/ — AGENT.md is the single source of truth for the agent's behavior (build order, container library versions, rules). Tool-agnostic; template/README.md covers opencode, Claude Code, Cursor, and plain chat.
  • .opencode/ — thin adapter wiring template/AGENT.md into opencode's subagent system.
  • examples/ — drop complete Mythic bundles here; the agent uses them as an alternative reference source alongside the docs.
  • ornn-agent/ — self-contained product built with this setup; bundles the docs inside the container. See ornn-agent/README.md.

Requirements

  • Docker + a Mythic install to build and run generated agents
  • Any coding agent that can read a markdown prompt file, or an OpenAI-compatible endpoint for build mode

Attribution

  • mythic-doc/ is a pruned copy of the official Mythic docs (github.com/MythicMeta/Mintlify_Documentation). See NOTICE for attribution and license status. Mythic itself is BSD 3-Clause.
  • Thanks to Adam Chester(@xpn) of SpecterOps for the idea and his post: Disposable Tooling: Building LLM-Generated Mythic Agents from Prompt to Deployment
Download Tool

Most Popular

View all →

Discover the most used tools by our community.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 The ultimate OSINT toolkit: investigation graph, confidence scoring, alias families, map, timeline and reports. 49 modules, 400+ sites, no API keys required.

    755
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    GhostLock One-Tap Execution App (CVE-2026-43499)

    510
  • 3

    ARTEX

    baarai/artex

    LLM multi-agent autonomous penetration testing platform with planner/worker agents, asset and exploration graphs, MITM traffic recording, and vulnerability retesting.

    415
  • 4

    redforge

    cybersecurity91/redforge

    Browser-side red team toolkit with 102 offline tools for recon, payload generation, credential attacks, crypto, encoding and engagement reporting.

    343
  • 5

    antifox

    antifox-ai/antifox

    AI multi-agent autonomous penetration testing platform that runs recon, attack-surface discovery, exploitation validation and evidence-backed report delivery.

    259
  • 6

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

    258

Explore all tools

Browse our collection of tools

View all tools →