Decepticon AI Agent

<div align="center"> <img src="assets/logo_banner.png" alt="Decepticon Logo"> </div> <h1 align="center">Decepticon — Autonomous Red Team Agent</h1> <p align="center"><i>"Another AI hacker? Let us guess — it runs nmap and writes a report."</i></p> <div align="center">

<a href="https://trendshift.io/repositories/15987?utm_source=repository-badge&amp;utm_medium=badge&amp;utm_campaign=badge-repository-15987" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/repositories/15987" alt="BitterSecurity%2FDecepticon | Trendshift" width="250" height="55"/></a> <a href="https://trendshift.io/repositories/15987?utm_source=trendshift-badge&amp;utm_medium=badge&amp;utm_campaign=badge-trendshift-15987" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/15987/daily?language=Python" alt="BitterSecurity%2FDecepticon | Trendshift" width="250" height="55"/></a>

<br/> <a href="https://github.com/BitterSecurity/Decepticon/blob/main/LICENSE"> <img src="https://img.shields.io/github/license/BitterSecurity/Decepticon?style=for-the-badge&color=blue" alt="License: Apache 2.0"> </a> <a href="https://github.com/BitterSecurity/Decepticon/stargazers"> <img src="https://img.shields.io/github/stars/BitterSecurity/Decepticon?style=for-the-badge&color=yellow" alt="Stargazers"> </a> <a href="https://github.com/BitterSecurity/Decepticon/graphs/contributors"> <img src="https://img.shields.io/github/contributors/BitterSecurity/Decepticon?style=for-the-badge&color=orange" alt="Contributors"> </a> <br/> <a href="https://discord.gg/TZUYsZgrRG"> <img src="https://img.shields.io/badge/Discord-Join%20Us-7289DA?logo=discord&logoColor=white&style=for-the-badge" alt="Join us on Discord"> </a> <a href="https://decepticon.red"> <img src="https://img.shields.io/badge/Website-decepticon.red-brightgreen?logo=vercel&logoColor=white&style=for-the-badge" alt="Website"> </a> <a href="https://docs.decepticon.red"> <img src="https://img.shields.io/badge/Docs-docs.decepticon.red-8B5CF6?logo=bookstack&logoColor=white&style=for-the-badge" alt="Documentation"> </a> <a href="https://app.decepticon.red"> <img src="https://img.shields.io/badge/Live%20App-app.decepticon.red-FF2D55?logo=rocket&logoColor=white&style=for-the-badge" alt="Live hosted app"> </a> </div> <br/> <div align="center"> <p><strong>Commercial product demo</strong></p> <video src="https://github.com/user-attachments/assets/7a9b233c-fd72-4633-a408-03953c345a15" width="800" controls></video> </div> <div align="center">

☁️ Don't want to self-host? Decepticon is live in the cloud.

Skip the Docker setup — run autonomous red-team engagements right from your browser.

<a href="https://app.decepticon.red"> <img src="https://img.shields.io/badge/Launch%20the%20Live%20App-app.decepticon.red-FF2D55?logo=rocket&logoColor=white&style=for-the-badge" alt="Launch the live app at app.decepticon.red"> </a> </div> <div align="center"> <p><strong>Open-source CLI demo</strong></p> <video src="https://github.com/user-attachments/assets/b3fd40d8-e859-4a39-97f4-bd825694ad96" width="800" controls></video> </div>

---

Install

Prerequisites: Docker and Docker Compose v2. Supported on macOS (Apple Silicon + Intel), Linux (amd64 + arm64), and Windows (amd64 + arm64) — native via PowerShell or via WSL2 (Ubuntu / Kali).

macOS / Linux / WSL2

curl -fsSL https://decepticon.red/install | bash
decepticon onboard   # Interactive setup wizard (provider, API key, model profile)
decepticon           # Start the core stack and drop into the terminal CLI

The default start brings up the core management plane (LiteLLM, PostgreSQL, Neo4j, Skillogy, LangGraph, sandbox) and launches the terminal CLI. Specialist workloads (BloodHound CE, Sliver C2, REA/Ghidra, …) come up on demand — the orchestrator spawns them via ops_start("ad") etc. The terminal CLI is the OSS operator interface; the hosted web console is part of Decepticon Cloud.

Windows (PowerShell, native)

irm https://decepticon.red/install.ps1 | iex
decepticon onboard
decepticon

→ Quick start · Full setup walkthrough

Inside the interactive CLI

Type / to browse commands, select with Up/Down, then press Enter. Tab completes the selected command; aliases also appear in help and autocomplete.

Command	Use
/help, /shortcuts	Discover commands or keyboard shortcuts
/model, /status	Choose a configured model or inspect session connections
/plan	Enter optional Plan mode, then send your planning message
/mode red, /mode blue	Return to Red or select Blue investigation
/new	Start a fresh conversation in the same engagement and mode when idle
/sessions, /resume	Browse saved conversations or continue paused work
/version (/about), /pwd (/cwd)	Check the running version and workspace paths
/quit, /exit	Leave the chat; services and server work keep running

Enter sends; Shift+Enter, Alt+Enter or Ctrl+J adds a line. Up/Down recalls input history at the first/last input row; Ctrl+R searches it. Esc closes focused UI first, then pauses active work; /resume continues it. Ctrl+A moves to the start of the current line. Use /queue to review waiting messages before /new.

/new preserves saved conversations and terminal scrollback; it does not create another engagement or change target authorization. /plan and /new take no arguments.

The new shortcuts and slash conveniences above describe current main, including unreleased changes. A source merge does not update installed images. See version history, the complete CLI reference and upgrade behavior.

Use from Claude Code or Codex

After starting Decepticon, register its MCP server in your coding agent:

claude mcp add --scope user decepticon -- decepticon mcp serve
codex mcp add decepticon -- decepticon mcp serve

Use the command for the coding agent you have installed, then run decepticon skill install to add the operator guide to both agents. See the external agent guide for the Agent Skill, tool workflow, and source installation path.

Use as a library (pip)

Building on top of the agents — a product, a research integration, or a custom orchestrator? Install the SDK from PyPI:

pip install decepticon              # core SDK
pip install "decepticon[neo4j]"     # + the knowledge-graph attack-chain tools

decepticon is a client SDK: it ships the agent factories, middleware, tools, and skills, and routes LLM calls and sandbox execution to runtime services over HTTP (DECEPTICON_LLM__PROXY_URL, SANDBOX_URL). Running agents still needs those services — use the Docker stack above, or point the URLs at your own equivalents. See Decepticon as a library for the factory override surface, declarative PluginBundle plugins, and the safety gate.

---

💖 Support Decepticon

We're building Decepticon toward an Offensive Vaccine for the AI-driven threat landscape. If you believe in autonomous red teaming as a path to stronger defense, consider supporting the project.

---

Benchmark

<div align="center"> <img src="assets/benchmark/decepticon_donut.png" alt="Decepticon — XBOW pass rate 102/104 (98.08%)" width="560"> </div>

Benchmark	Difficulty	Pass Rate
XBOW validation-benchmarks	Easy (Level 1)	45 / 45 (100 %)
XBOW validation-benchmarks	Medium (Level 2)	50 / 51 (98.0 %)
XBOW validation-benchmarks	Hard (Level 3)	7 / 8 (87.5 %)
XBOW validation-benchmarks	All levels	102 / 104 (98.08 %)

• Full per-challenge index, attack-class matrix, and LangSmith traces
• Comparison vs other AI pentest agents (Strix, PentestGPT, MAPTA, Cyber-AutoAgent, XBOW commercial, …)

---

What is Decepticon?

The "AI + hacking" space is full of demos that run nmap and print a report. That's not what this is.

Decepticon is a professional autonomous Red Team agent. It executes realistic attack chains — reconnaissance, exploitation, privilege escalation, lateral movement, C2 — the way a real adversary would, not the way a scanner does.

Every Red engagement starts with an operator-approved target and RoE. Optional Plan mode adds Soundwave's discussion and seven planning documents alongside the read-only RoE. The execution orchestrator owns OPPLAN; Plan is not required for Red.

→ Engagement workflow deep dive

---

Why Decepticon?

Real kill chains, not checkbox scans. Decepticon reads an OPPLAN and pursues objectives through whatever path opens up — pivoting, adapting, chaining techniques.

Interactive shells, actually. Real offensive tools are interactive (msfconsole, sliver-client, evil-winrm). Decepticon runs every command inside persistent tmux sessions with automatic prompt detection — so when a tool drops into an interactive prompt, the agent sends follow-up commands without workarounds.

Hardened sandbox isolation. All commands run inside a Kali Linux sandbox on a dedicated operational network (sandbox-net), separate from the management plane (decepticon-net). LangGraph drives the sandbox via the Docker socket. → Architecture

Offense serves defense. The planned Offensive Vaccine loop will turn findings into defense improvements through an attack → defend → verify cycle.

---

Architecture

<div align="center"> <img src="assets/decepticon_infra.svg" alt="Decepticon Infrastructure" width="680"> </div>

Two-network design. The always-on management plane (LiteLLM, PostgreSQL, Skillogy, LangGraph) and the always-on sandbox plane stay up across the whole engagement; everything else is dynamic-spawn — specialist workloads (BloodHound CE, Sliver C2, REA/Ghidra, …) come up only when the orchestrator calls ops_start(...) (see ADR-0006). Networks: management on decepticon-net; sandbox + C2 server + targets on sandbox-net. Neo4j is dual-homed so the agent (on management) can persist findings written from inside the sandbox.

→ Architecture deep dive · Knowledge graph

---

Agents

16 specialist agents organized by kill chain phase, with a fresh context window per objective — no accumulated noise.

Orchestration · Reconnaissance · Exploitation · Post-Exploitation · Vulnerability Research · Domain Specialists (AD, Cloud, Smart Contracts, Reversing, Analyst).

→ Full agent roster and middleware stack

---

Models & Providers

Tier-based, credentials-aware fallback chain. You declare which credentials you have in priority order; Decepticon builds the primary→fallback chain at every tier from there.

Profile	Tier per agent	Use case
eco (default)	Per-agent (HIGH for orchestrator/exploiter/patcher/analyst, MID for execution, LOW for recon/soundwave)	Production
max	Every agent on HIGH	High-value targets
test	Every agent on LOW	Development / CI

Tier-mapped providers: Anthropic, OpenAI, Google Gemini, MiniMax, DeepSeek, xAI, Mistral, OpenRouter, Nvidia NIM, Ollama (local). Subscription OAuth: Claude Max/Pro/Team, ChatGPT Pro/Plus/Team, Gemini Advanced, Copilot Pro, SuperGrok, Perplexity Pro.

Configure via decepticon onboard. → Full model reference & fallback examples

---

Documentation

Topic	Doc
Installation and first engagement	Getting Started
Complete setup, OAuth and providers	Setup Guide
Coding-agent CLI wrapper	Decepticon skill
Documentation and repository map	Documentation index
All CLI commands and keyboard shortcuts	CLI Reference
All make targets	Makefile Reference
Agent roster and middleware	Agents
REA/Ghidra reverse engineering	REA Reversing
Local defensive monitoring	Blue Cell
Model profiles and fallback chain	Models
Skill system and format spec	Skills
Extending capabilities, skills, workflows and clients	Extension contract
System architecture and network isolation	Architecture
Neo4j knowledge graph	Knowledge Graph
End-to-end engagement workflow	Engagement Workflow
Offensive Vaccine loop	Offensive Vaccine
Release history	Changelog
Contributing to Decepticon	Contributing

---

Contributing

git clone https://github.com/BitterSecurity/Decepticon.git
cd Decepticon
make dogfood  # Full OSS UX (launcher → onboard → CLI) on local code
make dev      # Backend hot-reload (compose watch) — daily dev loop

→ Contributing guide

---

Community

Join the Discord — ask questions, share engagement logs, discuss techniques.

---

Disclaimer

Do not use this project on any system or network without explicit written authorization from the system owner. Unauthorized access to computer systems is illegal. You are solely responsible for your actions. The authors and contributors assume no liability for misuse.

---

License

Apache-2.0

---

Acknowledgements

Thanks to the maintainers and contributors of the projects Decepticon builds on, integrates, and learns from.

Project	Role in Decepticon
REA and Ghidra	Optional reverse engineering workload and evidence-backed binary analysis. Integration details.
Deep Agents and LangGraph	Agent harness, orchestration, streaming and persistent execution state.
LiteLLM	Model gateway and provider routing.
insane-search	Upstream engine adapted for sandbox web access. Adaptation notice.
Playwright	Browser automation for web investigation.
Caddy and Fluent Bit	Local Blue sensor ingress and log collection. Blue Cell architecture.
Ink, Bubble Tea and Huh	Interactive CLI rendering and launcher forms.
PayloadsAllTheThings, h4cker and Awesome-Hacking	Security knowledge and learning references. Attribution details.
XBOW validation benchmarks	Evaluation tasks used by the benchmark integration. Results and methodology.

For CLI interaction design, we also studied Claude Code, Codex CLI and Gemini CLI. The CLI reference review records the resulting choices.

Upstream licenses and attribution notices remain applicable; see third-party licenses and the notices alongside adapted code.