Skip to main content
Majordomo sits between your application and your LLM providers. One config change routes your requests through the gateway, and you immediately get cost tracking, request logging, replay, and evaluations — without modifying your application logic.

Quick Start

Connect to Majordomo in minutes. Change one line of code and start logging requests.

How It Works

Learn how Majordomo proxies your LLM requests and what data goes where.

Connect Your Code

Integration examples for OpenAI, Anthropic, Gemini, and more SDKs.

Replay & Evals

Test a model switch against real production traffic before you commit.

​
What Majordomo gives you

Cost & Usage Tracking

Every request logged with model, tokens, cost, and latency. Break down spend by team, feature, environment, or user with custom metadata headers.

Replay

Run real production traffic against a candidate model. Get actual cost, latency, and quality numbers on your workload before you switch.

Evals

Build test suites from logged requests. Define scoring criteria. Run scored evaluations against any model before a change ships.

Multi-provider Routing

OpenAI, Anthropic, and Gemini from a single endpoint. Switch models in the dashboard without touching application code.

​
Get up and running

1

Create an account

Sign up at app.gomajordomo.com and create your first API key from the API Keys section.
2

Point your SDK at the gateway

Change the base URL to https://gateway.gomajordomo.com/v1 and add your X-Majordomo-Key header. No other changes required.
3

Verify in the dashboard

Send a request. It appears in the dashboard immediately with model, token counts, cost, and latency.
4

Add metadata for cost attribution

Tag requests with X-Majordomo-Feature, X-Majordomo-Team, and other custom headers to break down spend across any dimension.

​
Two deployment modes

Managed — Majordomo runs the gateway. Point your SDK at the gateway endpoint, create an API key, and you’re logging requests within minutes. No infrastructure to operate. Self-hosted Steward — You run Steward inside your own VPC. Your prompts and completions never leave your infrastructure. Majordomo receives only metadata — token counts, cost, latency, model name. The right choice for teams with data residency requirements.

Self-hosted Setup

Run Steward in your own VPC. Step-by-step setup with Docker, Postgres, and optional S3/GCS body storage.