# Majordomo

- [Introduction](https://docs.gomajordomo.com/introduction.md): Majordomo is the control plane for your AI stack: routing, cost visibility, replay, and evals across every LLM request your team makes.
- [Quick Start](https://docs.gomajordomo.com/quickstart.md): Start logging LLM requests to production in minutes.
- [How It Works](https://docs.gomajordomo.com/architecture/how-it-works.md): Majordomo is a transparent proxy. Your prompts go to your bucket. Metadata goes to Majordomo.
- [Components](https://docs.gomajordomo.com/architecture/components.md): What Steward, Butler, and the Web app do, and how they fit together.
- [Connect Your Code](https://docs.gomajordomo.com/integrations/connect.md): Point any SDK at the Majordomo gateway with one config change.
- [Set Up with Claude Code](https://docs.gomajordomo.com/integrations/claude-code.md): Install the Majordomo skills so Claude Code wires the gateway and library into your codebase for you.
- [Metadata Keys](https://docs.gomajordomo.com/guides/metadata-keys.md): Discover, name, and activate metadata keys to power fast filtering and breakdowns in usage, Replay, and Evals.
- [Cost Attribution](https://docs.gomajordomo.com/guides/cost-attribution.md): Tag every LLM request with custom metadata and break down spend by team, feature, environment, or any dimension you care about.
- [Agent Run Tracking](https://docs.gomajordomo.com/guides/agent-runs.md): Group the many LLM calls of one conversation or agent run into a single run, with a rolled-up cost and a nested waterfall of which step drove which calls.
- [Replay](https://docs.gomajordomo.com/guides/replay.md): Take real production traffic and replay it against a different model. Compare cost, latency, and output quality before you switch.
- [Evals](https://docs.gomajordomo.com/guides/evals.md): Build evaluation sets from logged requests. Define scoring criteria. Run evals against any model before you ship.
- [Provider Routing](https://docs.gomajordomo.com/guides/routing.md): Send a request to a model instead of a provider, and let the gateway pick the cheapest healthy endpoint that can serve it.
- [Cloud Body Storage](https://docs.gomajordomo.com/configuration/cloud-storage.md): Configure per-user or per-organization cloud storage so Steward uploads full request/response bodies to your own S3 or GCS bucket.
- [API Keys](https://docs.gomajordomo.com/configuration/api-keys.md): Create and manage Majordomo API keys.
- [CLI](https://docs.gomajordomo.com/configuration/cli.md): Install and use the Majordomo CLI to authenticate and manage API keys and Steward instances from your terminal.
- [Steward Setup](https://docs.gomajordomo.com/enterprise/steward-setup.md): Run the Majordomo Steward in your own VPC. Your prompts never leave your infrastructure.
- [Enterprise Security](https://docs.gomajordomo.com/guides/enterprise-security.md): Answer security questionnaires, pass vendor reviews, and give your security team what they need, without changing how your product works.
- [Request Headers](https://docs.gomajordomo.com/reference/headers.md): Complete reference for X-Majordomo-* headers.
- [Data Model](https://docs.gomajordomo.com/reference/schema.md): Reference for core tables written by Steward and queried by the dashboard.
- [Configuration Reference](https://docs.gomajordomo.com/configuration/overview.md): All environment variables for the Majordomo Steward.

## OpenAPI Specs

- [openapi](/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/go-majordomo/majordomo-gateway)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.