# AnchorShell

> AnchorShell builds self-hostable and managed infrastructure for AI applications. Its first product, Relay, is an LLM gateway for routing, queueing, limits, and observability.

## Relay

- [AnchorShell Relay](https://anchorshell.com/products/relay): Self-host Relay for free. Get ordered model routing, queueing, pacing, fallback, guardrails, and realtime observability—or start with our hosted free tier.
- [Pricing and deployment options](https://anchorshell.com/pricing)
- [Gateway capability comparison](https://anchorshell.com/compare)

## Getting Started

- [Getting Started](https://anchorshell.com/docs/getting-started.md): Add a provider, choose a model, and send your first request with hosted AnchorShell Relay.
- [Self-hosted](https://anchorshell.com/docs/self-hosting.md): Install AnchorShell Relay, find your local keys, and send a request from your own machine.

## Model Relay

- [Dashboard](https://anchorshell.com/docs/dashboard.md): Check Relay setup, current activity, model health, and usage at a glance.
- [Realtime](https://anchorshell.com/docs/realtime.md): Watch requests wait, run, and finish across your configured models.
- [Providers](https://anchorshell.com/docs/providers.md): Understand providers, credentials, and configured models; add them in the dashboard or through the API.
- [Groups](https://anchorshell.com/docs/groups.md): Create ordered regular Groups or request-aware Smart Groups, arrange models, and call either through the model field.
- [Guardrails](https://anchorshell.com/docs/guardrails.md): Apply an HTTP policy before a model call or after its response, with explicit bindings and failure behavior.
- [Limits](https://anchorshell.com/docs/limits.md): Control requests, tokens, spending, and concurrency without confusing resource limits with individual budgets.
- [Usage](https://anchorshell.com/docs/usage.md): Review request counts, token use, and configured costs by model, provider, user, or API key.
- [Queue](https://anchorshell.com/docs/queue.md): Inspect requests waiting for capacity and cancel work you no longer need.
- [Logs](https://anchorshell.com/docs/logs.md): Find a request and inspect its result, timing, selected model, usage, and guardrail outcome.
- [Playground](https://anchorshell.com/docs/playground.md): Send a test request, inspect the response, and copy a curl command for your application.
- [Settings](https://anchorshell.com/docs/settings.md): Adjust Relay defaults, estimate-based admission, and request-payload storage.
- [Setup](https://anchorshell.com/docs/setup.md): Use the guided setup to connect a provider and model, choose grouping, and send a first request.

## Account

- [Account](https://anchorshell.com/docs/account.md): Update your profile, verify a new email address, and choose whether to receive product updates.
- [Security](https://anchorshell.com/docs/security.md): Change your password and remove access from sessions you no longer recognize.
- [API Keys](https://anchorshell.com/docs/api-keys.md): Create, scope, rename, and revoke individually attributable hosted API keys.
- [Billing](https://anchorshell.com/docs/billing.md): View your plan, review changes, manage seats, and open billing history.
- [Team](https://anchorshell.com/docs/team.md): Invite teammates, assign access, and manage shared Relay configuration without sharing credentials.

## API

- [API](https://anchorshell.com/docs/api.md): Authenticate hosted management and inference calls with scoped API keys. Use separate tokens for self-hosted Relay.
- [Hosted OpenAPI](https://anchorshell.com/openapi.json)
- [Self-hosted inference OpenAPI](https://anchorshell.com/openapi-self-hosted.json)

## Guides

- [Send your first managed request](https://anchorshell.com/guides/managed-first-request.md): Create a User API key and send one request through the managed AnchorShell Relay API.
- [Create and call a Smart Group](https://anchorshell.com/guides/create-smart-group.md): Create intent assignments, review the Model order, and call a Smart Group.
- [Connect a provider account](https://anchorshell.com/guides/connect-provider-account.md): Authorize a supported model account, verify it, and enable discovered Models in AnchorShell Pro.
- [Create an agent User API key and limit](https://anchorshell.com/guides/create-agent-api-key-limit.md): Create one user-owned agent key and enforce an exact request, token, or spend policy.
- [Grant provider access](https://anchorshell.com/guides/grant-provider-access.md): Grant organization, user, or exact-key use of a connected subscription account.
- [Self-host Relay from source](https://anchorshell.com/guides/self-host-bouncer.md): Clone the public Relay repository, start the embedded application, and protect its first-run secrets.
- [Send a request through the dummy model](https://anchorshell.com/guides/dummy-model-first-request.md): Configure Relay's built-in dummy provider and verify the routed gateway without an external account.
- [Add a provider, model, and group](https://anchorshell.com/guides/add-provider-model-group.md): Connect an upstream account and expose its model through an ordered Relay group.
- [Build a free, local, and paid model order](https://anchorshell.com/guides/free-local-paid-group.md): Create an explicit model order that uses free or local capacity before a paid fallback.
- [Tune wait budgets, pacing, and cooldowns](https://anchorshell.com/guides/tune-wait-pacing-cooldowns.md): Control when Relay waits for a preferred model and when it evaluates a fallback.
- [Configure guardrails before and after a model call](https://anchorshell.com/guides/configure-guardrails.md): Bind an external policy service to a Group, Provider, or Model and verify both lifecycle stages.
- [Handle provider 429 responses](https://anchorshell.com/guides/handle-provider-429s.md): Test Relay cooldown and requeue behavior without creating a retry storm.
- [Inspect a request trace and reconcile cost](https://anchorshell.com/guides/inspect-request-trace.md): Use Logs and optional OpenTelemetry traces to explain routing, timing, tokens, and cost.

## Source / Releases

- [Official Relay source](https://github.com/anchorshell/bouncer)
- [Changelog](https://anchorshell.com/changelog)
- [Releases](https://anchorshell.com/releases)

## Complete documentation

- [Consolidated public documentation](https://anchorshell.com/llms-full.txt)