Deploy AI agent governance in 3 steps. One container, no code changes, no engineering sprint.
The D3cipher Gateway is a Docker container you deploy in your own infrastructure. Your AI agents talk to it instead of directly to OpenAI, Anthropic, or any other provider. The gateway enforces governance policies — audit trail, kill switch, token budgets, encrypted transcripts — without touching a single line of agent code.
Your prompts and responses never leave your network in plaintext. Only cryptographic stamps and encrypted blobs reach the D3cipher cloud. The server cannot read your content. Only your Account Key can decrypt it.
Your Agent D3cipher Gateway AI Provider
(no changes) (your network) (OpenAI, etc.)
| | |
|--- API request ---->| |
| |-- stamp (metadata) ----->| D3cipher Cloud
| |-- encrypt body --------->| (can't read it)
| | |
| |--- forward request ----->|
| |<-- provider response ----|
| | |
| |-- stamp response ------->| D3cipher Cloud
| |-- encrypt response ----->| (can't read it)
|<-- response --------| |
| | |
Sign in at d3cipher.ai/dashboard. Your dashboard gives you two things:
lsk_admin_... (found in Settings)Account Key is optional but recommended. Without it, you still get the full audit trail and kill switch. With it, you also get encrypted transcript replay — the ability to read the exact prompts and responses your agents processed, decrypted entirely in your browser. The server never sees your Account Key.
Send IT the API Key and Account Key (if using encrypted transcripts) along with this page.
Run one container in your infrastructure:
docker run -d --name d3cipher-gateway \ -e D3CIPHER_API_KEY=lsk_admin_your_key_here \ -e UPSTREAM_URL=https://api.openai.com \ -e ACCOUNT_KEY=your_64char_hex_account_key \ -p 4000:4000 \ d3cipher/gateway:latest
| Variable | Description |
|---|---|
D3CIPHER_API_KEY required |
API key from your D3cipher dashboard. Authenticates the gateway with the D3cipher cloud. |
UPSTREAM_URL required |
The AI provider your agents call. Examples: https://api.openai.com, https://api.anthropic.com, https://bedrock-runtime.us-east-1.amazonaws.com |
ACCOUNT_KEY optional |
64-character hex key for encrypted transcript storage. Enables the Auditor tab in your dashboard. Without it, you still get audit trail + kill switch. |
AGENT_ID optional |
Default agent name when agents don't identify themselves via header. If not set, each agent must send the X-D3cipher-Agent header. |
LOCKSTOCK_URL optional |
Override the D3cipher cloud URL. Only needed for on-premise deployments. Defaults to production. |
Verify it's running:
curl http://localhost:4000/healthz
# {"status": "ok", "agents_active": 0, "inflight": 0}
Kubernetes? The gateway exposes /healthz for liveness probes
and /metrics for Prometheus scraping. Single replica recommended (agent state is in-memory).
Change one environment variable wherever your agents run:
# Before (direct to OpenAI) OPENAI_BASE_URL=https://api.openai.com # After (through D3cipher Gateway) OPENAI_BASE_URL=http://gateway-host:4000
To identify which agent is which in the dashboard, add one HTTP header to each agent's configuration:
X-D3cipher-Agent: customer-support-bot
If all your agents share a single identity (or you only have one agent), set AGENT_ID
on the container instead and skip the header.
That's it. No SDK to install. No middleware to inject. No code changes. The agents think they're talking to OpenAI. They're actually talking to a gateway in your own network that enforces your governance policies.
Refresh your dashboard. Agents appear as they make their first call.
Lock any agent instantly from the dashboard. The gateway returns a 429 error to the agent. The request never reaches the AI provider. Unlock when ready.
Set per-agent spending limits. When an agent exhausts its token budget, the circuit breaker
trips automatically. The gateway also clamps max_tokens on each request to prevent
a single call from blowing the remaining budget.
If you provided an Account Key, open the Auditor tab in the dashboard. Enter your key. Read the full content of every prompt and response, decrypted entirely in your browser. The D3cipher server stores only ciphertext it cannot read.
Sentinel ML monitors agent request velocity using Welford online statistics. Unusual spikes trigger alerts. The circuit breaker can automatically halt agents that exceed defined thresholds.
Prompts and completions. API keys. Customer data. Request and response bodies. The Account Key. Everything that matters stays behind your firewall.
Agent ID. Task type. Timestamp. Token count. Sequence number. Cryptographic hashes. Encrypted blobs (that only your Account Key can decrypt). Governance metadata — not your data.
version: "3.8"
services:
d3cipher-gateway:
image: d3cipher/gateway:latest
ports:
- "4000:4000"
environment:
D3CIPHER_API_KEY: "${D3CIPHER_API_KEY}"
UPSTREAM_URL: "https://api.openai.com"
ACCOUNT_KEY: "${ACCOUNT_KEY}"
restart: unless-stopped
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:4000/healthz"]
interval: 30s
timeout: 5s
retries: 3
apiVersion: apps/v1
kind: Deployment
metadata:
name: d3cipher-gateway
spec:
replicas: 1
selector:
matchLabels:
app: d3cipher-gateway
template:
metadata:
labels:
app: d3cipher-gateway
spec:
containers:
- name: gateway
image: d3cipher/gateway:latest
ports:
- containerPort: 4000
env:
- name: D3CIPHER_API_KEY
valueFrom:
secretKeyRef:
name: d3cipher-secrets
key: api-key
- name: UPSTREAM_URL
value: "https://api.openai.com"
- name: ACCOUNT_KEY
valueFrom:
secretKeyRef:
name: d3cipher-secrets
key: account-key
livenessProbe:
httpGet:
path: /healthz
port: 4000
initialDelaySeconds: 5
periodSeconds: 30
resources:
requests:
memory: "128Mi"
cpu: "100m"
limits:
memory: "512Mi"
cpu: "500m"
---
apiVersion: v1
kind: Service
metadata:
name: d3cipher-gateway
spec:
selector:
app: d3cipher-gateway
ports:
- port: 4000
targetPort: 4000
type: ClusterIP
Single replica recommended. The gateway maintains per-agent state in memory (DEK cache, budget tracking, connection pools). Multiple replicas would create independent state per pod. Horizontal scaling is on the roadmap.
| Path | Purpose |
|---|---|
/healthz |
Liveness probe. Returns 200 if gateway is up and D3cipher cloud is reachable, 503 if degraded. |
/metrics |
Prometheus-compatible metrics: request count, rejection count, and latency per agent. |
/* |
Everything else is proxied to UPSTREAM_URL through LockStock governance middleware. |
Gateway returns 400 "Missing X-D3cipher-Agent header": Either set AGENT_ID on the container for a default, or add the X-D3cipher-Agent header to each agent's HTTP requests.
Gateway returns 429 "Token budget exhausted": The agent's token budget is depleted. Go to the dashboard, increase the budget or click Unlock to reset the counter.
Gateway returns 503 "LockStock stamp rejected": The circuit breaker has tripped (velocity anomaly or manual lock). Check the dashboard for the reason. Click Unlock to restore access.
/healthz returns 503: The gateway can't reach the D3cipher cloud. Check network connectivity and LOCKSTOCK_URL if set.
Agents not appearing in dashboard: Make sure the agents are actually sending requests through the gateway (check OPENAI_BASE_URL points to the gateway, not directly to OpenAI).
Transcripts show "Blob not available": The ACCOUNT_KEY environment variable wasn't set when those requests were processed. Set it and future transcripts will be encrypted and stored.
The gateway is the recommended deployment for most organizations. If you need to embed governance directly into agent code (e.g., for agents that can't route through a proxy), see the Compliance Quickstart for the per-agent middleware approach.