Quickstart — 15 minutes to assessor-reviewable

Deploy HoundShield in 15 minutes.

By the end of this guide your team's AI usage will be intercepted, classified, and generating an audit trail your C3PAO assessor can verify.

No firewall rulesNo network changesWorks with any AI SDK

Prerequisites

Docker Desktop installed and running — download here
HoundShield license key — get one free
Your AI provider API key (OpenAI, Anthropic, Google, or OpenRouter)

Run the installer

~2 min

One curl command pulls the Docker image, starts the proxy, and confirms it's running. Requires Docker Desktop.

bash

curl -sSL https://houndshield.com/install | bash

Or non-interactive: HOUNDSHIELD_LICENSE_KEY=<key> UPSTREAM_API_KEY=<key> bash install.sh -y

Change one environment variable

~30 sec

Replace your AI provider's base URL with the proxy. Every SDK that speaks OpenAI-compatible APIs works — ChatGPT, Copilot, Claude, Gemini.

bash

# .env or your shell profile
OPENAI_BASE_URL=http://localhost:8080/v1
# ANTHROPIC_BASE_URL=http://localhost:8080/v1  # Claude
# GOOGLE_BASE_URL=http://localhost:8080/v1      # Gemini

Test: send a CUI prompt

~30 sec

Verify the proxy is intercepting. This prompt contains a DoD contract number — it should be BLOCKED.

bash

curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role":"user","content":"W911NF-23-C-0001 status?"}]
  }'

Expected response: { "error": { "code": "content_policy_violation", "message": "BLOCKED — CUI detected" } }

Export your C3PAO audit report

~30 sec

Download a PDF that documents every AI prompt your team sent, which CMMC controls were triggered, and your SPRS impact. Hand this to your C3PAO.

bash

# From the dashboard — or via API:
curl "https://houndshield.com/api/reports/generate?format=pdf&from=2026-04-01T00:00:00Z&to=2026-04-30T23:59:59Z" \
  -H "Authorization: Bearer $HOUNDSHIELD_API_KEY" \
  --output cmmc-audit-report.pdf

Works with every AI provider

OpenAI / ChatGPT

OPENAI_BASE_URL=http://localhost:8080/v1

Anthropic / Claude

ANTHROPIC_BASE_URL=http://localhost:8080/v1

Google / Gemini

GOOGLE_BASE_URL=http://localhost:8080/v1

LangChainPython

openai = OpenAI(base_url="http://localhost:8080/v1")

LlamaIndexPython

llm = OpenAI(api_base='http://localhost:8080/v1')

OpenRouter800+ models

OPENROUTER_BASE_URL=http://localhost:8080/v1

You're protected.

Your C3PAO assessment PDF is one click away in the dashboard. Every AI prompt your team sends is now scanned, logged, and audit-ready.

Open Dashboard Download C3PAO PDF