ai-gateway

Route LLM API calls through a unified TrueFoundry AI Gateway.

2|1|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/passionseed/ps_app --skill ai-gateway-passionseed
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-gateway
Source: https://github.com/passionseed/ps_app/tree/main/.agents/skills/truefoundry-ai-gateway
Command: npx skills add https://github.com/passionseed/ps_app --skill ai-gateway-passionseed

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a unified gateway to access OpenAI-compatible LLMs through TrueFoundry, consolidating authentication, routing, rate limiting, and budget controls behind a single API.

Core Features & Use Cases

  • Single endpoint for cloud and self-hosted models with PAT or VAT-based authentication.
  • Flexible routing, load balancing, and observability to optimize model choice and cost.
  • Suitable for developers integrating OpenAI-compatible SDKs or curling requests to a centralized gateway in production environments.

Quick Start

Configure your gateway base URL and a PAT or VAT, then run a sample chat request to a configured model via the gateway endpoint.

Frequently Asked Questions about ai-gateway

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

FAQPage Schema
How do I route OpenAI-compatible LLM API calls through a unified gateway?

To route OpenAI-compatible LLM API calls through a unified gateway, configure your base URL and authenticate using a Personal Access Token or Virtual Access Token to enforce routing, load balancing, and budget controls.

What is an AI gateway and how does it simplify LLM access?

An AI gateway is a unified endpoint that simplifies LLM access by consolidating authentication, routing, rate limiting, and budget controls for both cloud and self-hosted models behind a single API.

Can I use the OpenAI SDK with self-hosted and cloud LLM providers?

Yes, you can use the OpenAI SDK with self-hosted and cloud LLM providers by routing requests through a TrueFoundry gateway endpoint, enabling access to a diverse model pool.

How do I set up per-user budgets and rate limiting for LLM API requests?

To set up per-user budgets and rate limiting for LLM API requests, configure gateway-model settings within your TrueFoundry instance, which automatically enforces quotas and security on all routed traffic.

Do I need a TrueFoundry instance to enforce LLM access control?

Yes, you need a TrueFoundry instance and gateway-model configuration to enforce routing, quotas, and security, along with a Personal Access Token or Virtual Access Token for authentication.

What are the limitations of using a centralized gateway for LLM access?

Limitations of using a centralized gateway for LLM access include the strict dependency on a TrueFoundry instance and the requirement of a PAT or VAT, meaning external TrueFoundry environments cannot authenticate.