AI governance gateway

Every AI request, governed.

agentKeyRoute sits between your AI tools and the models they use. Every request is identified, checked against your policy and compliance frameworks, redacted, routed to an allowed model, metered and written to a tamper-evident audit log.

Works with Claude Code, Codex, Cursor, the OpenAI and Anthropic SDKs, LangChain and your own apps.

Change one address. Keep your tools.

Point a tool at the gateway with a key from your console. The key carries the team, workload and governance profile, so the right rules apply without any change to the tool itself.

# Claude Code through agentKeyRoute
export ANTHROPIC_BASE_URL=https://gateway.agentkeyroute.com
export ANTHROPIC_AUTH_TOKEN=cvn_live_…
claude

How it works

Nine checks on every request, before anything leaves.

1

Identify & classify

The API key says who is calling and for which workload. The request is scanned for PHI, PII, card data, secrets, CUI and confidential material, using patterns, checksums and clinical context.

2

Redact & decide

Sensitive values are replaced before they reach a model. Ordered rules with default deny, risk scoring and optional guardrail models then decide: allow, hold or block.

3

Route, verify & record

Compliance frameworks become routing constraints, so data only goes to models allowed to see it. The model that answered is checked, and every request is metered and hash-chain audited.

Product

Control, evidence and cost in one place.

Data protection

Detection and redaction of regulated data, plus a prompt-injection guard and output scanning. Credentials and API keys are always blocked.

Policy-aware routing

Task-aware routing with fallback across your providers. When frameworks are combined, the strictest rule wins, and a request fails closed if the wrong model answers.

Guardrail models

Screen requests and responses with Llama Guard, ShieldGemma or Granite Guardian running on your own hardware. You choose whether to fail closed or fail open.

Tamper-evident audit

A full decision trace for every request, a hash-chained audit log with an integrity check, and evidence pack export for your auditors.

Cost & budgets

Every request metered by team, workload and person. Workload budgets, plan limits, chargeback, and import of Claude usage from outside the gateway.

Risk & incidents

A risk register with key risk indicators, automatic incidents for high-severity blocks, and kill switches to stop a workload at once.

For everyone, not only developers

Governed AI wherever people use it.

agentKeyRoute Chat

A chat window for everyone in the organisation. Every message follows the chat profile your administrators choose and is recorded under the person's name.

AI workspace

A coding agent in a private, hardened sandbox for each person. It can only use your governed models, with a key issued to that person.

Browser extension

Checks what people type into ChatGPT, Claude, Gemini, Copilot and Perplexity before it is sent. Your profile decides whether to allow it, redact it or block it.

Two-person control

Roles, teams, two-step sign-in, two-administrator approval for sensitive changes, and SIEM or webhook delivery of events.

Compliance

Frameworks that change behaviour, not just reports.

19 frameworks come with automated control checks, attestation and evidence export. 43 ready-made governance profiles cover healthcare, financial services, government, education, privacy and general use, and you can edit any of them.

Each API key carries a profile, and an effective-policy view shows exactly what that key can reach, and why.

  • HIPAA
  • HITRUST CSF
  • GDPR
  • EU AI Act
  • SOC 2
  • ISO/IEC 27001
  • ISO/IEC 42001
  • NIST AI RMF
  • PCI DSS
  • SOX
  • GLBA
  • NYDFS Part 500
  • DORA
  • FedRAMP
  • CMMC / NIST SP 800-171
  • CJIS
  • FERPA
  • CCPA / CPRA
  • DPDP Act (India)

Deployment

Your models, your network, your choice.

Cloud

Hosted by us. Connect your providers and start governing within minutes of approval.

Dedicated

An isolated instance for your organisation alone, on the Enterprise plan.

On-premises

Run the whole platform inside your own network, next to local models on Ollama, vLLM, TGI or NVIDIA NIM.

Pricing

Plans that grow with your AI use.

Starter

For a first governed AI use case.

$499 / month

  • 100,000 requests a month
  • 10 users · 5 API keys
  • 2 compliance frameworks
  • 90-day retention
  • Email support
Get started

Enterprise

Regulated enterprises, any deployment model.

Custom

  • Unlimited requests, users and keys
  • All compliance frameworks
  • Cloud, dedicated or on-premises
  • Bring your own key
  • 7-year retention
  • 24×7 support with 99.9% SLA
Apply

Prices in US dollars, excluding tax. Every new organisation is reviewed before it is activated.

Put every AI request under your policy.

Create your organisation, connect a provider and issue your first governed key.

Get started