Vanguard AI Routing Engine

One Endpoint for
All AI Providers

High-throughput routing gateway with model fallback, credential vaults, and zero latency overhead. Built for Claude Code, Codex, and agentic workflows.

Launch GatewayExplore Architecture

Get Started in 30 Seconds

Start z-router, configure your providers via web dashboard, and start routing AI requests.

1

Start z-router

Run Docker or local start command to launch server

2

Open Dashboard

Configure providers and API keys via web interface

3

Route Requests

Point your CLI tools to http://localhost:20128

bash
$docker compose up -dCopy
> Starting z-router...
> Server running on http://localhost:20128
> Dashboard: http://localhost:20128/dashboard
> Ready to route!
tuneConfigure providers in dashboard or use environment variables
Data Location:
Docker: ./data/db/data.sqlite
Local host: ~/.9router/db/data.sqlite

How z-router Works

Data flows seamlessly from your application through our intelligent routing layer to the best provider for the job.

terminal

CLI & Client Tools

Your requests start from your favorite tools or unified SDK. Simply redirect the base URL to z-router.

hub

Intelligent Routing

Our engine inspects token limits, checks provider health, and rotates across accounts for minimum latency.

smart_toymemoryclouddatabase

Upstream Fulfillment

Requests are fulfilled instantly across OpenAI, Anthropic, Gemini, or local models with automatic fallback.

Engine Capabilities

Engineered for Mission-Critical AI Routing

Everything you need to orchestrate and scale multi-provider intelligence without changing client code.

Core Protocol

Unified Endpoint

Access all 40+ providers via a single OpenAI-compatible standard API URL (/v1/chat/completions).

High Availability

Intelligent Model Fallback

Automatically cascade requests to healthy accounts or alternative models upon rate-limit, 429, or outage.

Zero-Overhead Delivery

Stream responses directly with zero latency buffer. Deploy anywhere with single-command Docker delivery.

Usage & Cost Analytics

Precise token accounting, active connection quotas, and cost tracking with SQLite persistence.

OAuth & Vault

Secure multi-account OAuth token auto-refresh and AES encrypted credential management.

CLI & Agent Native

Seamless integration with Claude Code, OpenAI Codex, Cline, Cursor, and agentic tool calls.

Ready to Simplify Your AI Infrastructure?

Join developers who are streamlining their AI integrations with z-router. Open source and free to start.