Skip to content
View NetVar1337's full-sized avatar
🔬
Reverse Engineering / Exploit Research / Security Audits
🔬
Reverse Engineering / Exploit Research / Security Audits
52 followers · 124 following

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex4Achievement: Galaxy Brainx4Achievement: YOLOAchievement: StarstruckAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex4Achievement: Galaxy Brainx4Achievement: YOLOAchievement: StarstruckAchievement: Quickdraw

Block or report NetVar1337

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
NetVar1337/README.md

Decepticon

NetVar

Co-Owner, Decepticon.red
Governed autonomous red-team operations · Discord: netvar

Building controlled, observable AI red-team capability for serious security work.

Decepticon.red

Decepticon.red is a governed AI red-team control plane for adversary emulation under rules set by the operator. It keeps autonomous execution bounded, observable, and tied to engagement evidence.

Product Open source
Decepticon.red — governed AI red-team operations PurpleAILAB/Decepticon — autonomous red-team agent

Operating model

  • Runtime governance — scope and Rules of Engagement are enforced before actions fire.
  • Execution discipline — the OPPLAN follows objectives, blockers, pivots, evidence, and next actions as an engagement evolves.
  • Specialist context — recon, initial access, and post-exploitation agents operate with ATT&CK and Skillogy knowledge.
  • Operator control — engagements remain observable and constrained by explicit operator decisions.

Research & tooling

Reverse engineering · exploit research · security audits

Project Focus
decepticon-ghidra-mcp Ghidra MCP tooling for P-code, BSim, version tracking, emulation, and agentic vulnerability research.
omniwire Infrastructure for AI agent swarms: MCP tooling, A2A coordination, networking, and browser automation.
unleash Bun SEA bytecode patch-analysis tooling with interactive workflows and signature scanning.

Connect

Pinned Loading

  1. PurpleAILAB/Decepticon PurpleAILAB/Decepticon Public

    Autonomous Hacking Agent for Red Team

    Python 4.7k 902

  2. omniwire omniwire Public

    Infrastructure layer for AI agent swarms — 88 MCP tools · A2A · OmniMesh VPN · Scrapling scraper · COC sync · nftables firewall · CDP browser · 2FA TOTP · ~80ms

    TypeScript 14 8

  3. unleash unleash Public

    Unleash Claude Code. 113 patches — zero refusals, zero telemetry, 42 feature gates unlocked. In-place Bun SEA bytecode patcher with interactive TUI, 11-strategy signature scanner, and auto-discover…

    Go 49 13

  4. Vigilo Vigilo Public

    Forked from PurpleAILAB/Vigilo

    An AI hacker for Web3 Smart Contract. for bug bounties, Audit contest, offensive security research, and real-world exploit thinking.

    TypeScript 3

  5. decepticon-ghidra-mcp decepticon-ghidra-mcp Public

    Most complete Ghidra MCP — 36 tools across P-code, BSim, Version Tracking, emulation, custom types. Built for agentic 0-day discovery.

    Java 1

  6. pcx-ai-toolkit pcx-ai-toolkit Public

    Source-grounded AI toolkit for Perception.cx Enma and AngelScript: verified docs, API oracle, validators, MCP tools, templates, skills, and LSP packages

    Python 12 1