Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.guardway.ai/llms.txt

Use this file to discover all available pages before exploring further.

Guardway is an LLM gateway you run inside your own network, governed from a SaaS dashboard at app.guardway.ai. The gateway is a single container that speaks an OpenAI-compatible API and fans requests out to 20+ providers (OpenAI, Anthropic, Google, Groq, Bedrock, Azure, Ollama, vLLM, and more). Guardrails, routing, budgets, caching, and tracing run locally; only aggregate telemetry reaches the cloud. Audit logs never leave the gateway. The dashboard is where you configure providers, attach them to gateways, sync models, test requests in the playground, and watch logs and traces.

​
The golden path

1. Sign up

Create your Guardway account and land on the dashboard.

2. Deploy a gateway

Run the gateway container in your network with a one-time registration token.

3. Activate it

Connect the dashboard to the running gateway.

4. Connect a provider

Add OpenAI, Anthropic, or any of 20+ presets. Attach to your gateway.

5. Sync models

Discover the models available on each provider from that gateway.

6. Test & observe

Send a request in the playground, then inspect logs and traces.

​
Who Guardway is for

Security-first enterprises

Banks, healthcare, government, and anyone with SOC 2, HIPAA, or PCI DSS obligations.

Teams who cannot send prompts to a third party

The gateway stays in your VPC. Audit logs are local-only.

Platforms with multi-tenant AI spend

Per-team budgets, per-key quotas, and per-provider cost tracking.

Developers tired of provider lock-in

One OpenAI-compatible endpoint, 20+ providers behind it.

​
Need help?

Email support@guardway.ai. For a guided walkthrough, start with the Quickstart.