Documentation Index
Fetch the complete documentation index at: https://docs.decepticon.red/llms.txt
Use this file to discover all available pages before exploring further.
Network Isolation
Decepticon’s architecture is built on a fundamental principle: the management infrastructure and operational infrastructure share zero network access. Two isolated Docker networks enforce this separation:Management Network (decepticon-net)
Houses the control plane:
| Component | Role |
|---|---|
| LangGraph Platform | Agent orchestration, SSE streaming, lifecycle management |
| LiteLLM Proxy | Model routing, provider fallback, API key management |
| PostgreSQL | Engagement state, findings, objective tracking, OPPLAN persistence |
| Web Dashboard | Next.js operator interface (Soundwave interview, attack-graph canvas, OPPLAN tracker) |
| Neo4j | Knowledge graph — bridges both networks so agents in the sandbox can write findings while the dashboard reads them from management |
Operational Network (sandbox-net)
Houses everything that touches targets:
| Component | Role |
|---|---|
| Kali Linux Sandbox | Full offensive toolkit — nmap, Sliver client, sqlmap, Impacket, and more |
| Sliver C2 Team Server | Command and control infrastructure (profile-based activation) |
| Target Infrastructure | Victim machines — Metasploitable, custom targets, or VPN access to real environments |
Why This Matters
This separation mirrors real Red Team infrastructure design:- No credential leakage — API keys and LLM tokens never exist on the operational network
- No cross-contamination — A compromised sandbox cannot reach the management plane
- Auditable boundaries — Clear network separation makes activity attribution straightforward
- Production-grade isolation — The same architecture you’d use for a real engagement
Docker Compose Architecture
All components are defined in Docker Compose with explicit network assignments:Agents
Learn about the seventeen specialist agents that operate within this infrastructure.
