ai-gateway

Route and orchestrate AI provider queries through a single API with failover and cost tracking.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/namhoangg/agent-starter-kit --skill ai-gateway-namhoangg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-gateway
Source: https://github.com/namhoangg/agent-starter-kit/tree/main/cursor/skills/ai-gateway
Command: npx skills add https://github.com/namhoangg/agent-starter-kit --skill ai-gateway-namhoangg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Consolidates AI provider routing, failover, cost tracking, and observability into a single, consistent API, reducing integration complexity and governance risk.

Core Features & Use Cases

  • Unified routing across multiple providers with automatic failover, latency-aware selection, and per-request routing control.
  • Cost attribution and budget governance through per-user tagging and observability dashboards.
  • End-to-end auditing, logs, and governance for multi-tenant workflows and compliance.

Quick Start

Install and configure a gateway-enabled client call to route model requests through AI Gateway and begin collecting per-user metrics.

Frequently Asked Questions about ai-gateway

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I route AI model requests across multiple providers with automatic failover?

Multi-provider routing channels requests through a single API with latency-aware selection and automatic failover. It reduces integration complexity by unifying provider management into one consistent endpoint.

How does cost tracking work for multi-tenant AI workloads?

Cost tracking for multi-tenant AI workloads uses per-user tagging and observability dashboards to attribute spending. This enables budget governance and provides per-request metrics for compliance.

What is the best way to add audit logging and observability to AI provider calls?

Adding audit logging and observability to AI provider calls requires a gateway that captures end-to-end logs and per-request metrics. This ensures compliance through governance guardrails on all routed queries.

Can I use a single API for cross-provider routing and budgeting?

A single API for cross-provider routing and budgeting consolidates authentication, caching, and latency observability. It allows per-request routing control while maintaining end-to-end governance.

Does AI gateway routing support per-user metrics and authentication?

AI gateway routing supports per-user metrics and authentication through unified API integration. It satisfies production-grade requirements for provider routing, caching, and audit logging within multi-tenant workflows.