Wyrd docs v0.4.1 Use with your coding agent Reference GitHub

Understand / Architecture

Architecture

A Wyrd deployment is one server binary, run as one pod or as several pods with different roles, behind one endpoint you own. It stores everything durable in Postgres and object storage, so pods can be replaced, scaled, or split by role without moving data.

Answers: What do I run for a team, and what does it connect to?
wyrd-server podsHTTPgRPCJWKSmodel callsYour appsSDKCICLICoding agentsMCPPeoplebrowserLoad balanceryours · TLSserverAPI · verification · LLM gatewayscribewrites · persistent diskoracleSQL queriesforge-workercompaction · no APIIdentity providerOIDC sign-inModel providersyour keysPostgresdeclarations · coordinationObject storageevidence · artifactsevery pod shares Postgres and object storage
Now

Every pod is the same wyrd-server binary; WYRD_TARGET picks its role. One pod running all is a complete deployment. Choose a step, or press Play.

Text version
  1. Every pod is the same wyrd-server binary; WYRD_TARGET picks its role. One pod running all is a complete deployment. Choose a step, or press Play.
  2. One endpoint. Every client reaches one address. Your load balancer terminates TLS and routes HTTP to API pods, Bifrost writes over gRPC to scribe pods, and queries to oracle pods. It never decides who the caller is; the Wyrd token does.
  3. Identity. People sign in through your OIDC provider. Apps, CI, and agents use API keys or workload identity. Every request is checked against the caller’s roles and tenant.
  4. Model calls. A model-judged check, or your app calling through the LLM gateway, reaches the provider from the server with your provider key. Each call is authorized and recorded.
  5. Storage. Postgres holds declarations, permissions, and coordination. Object storage holds evidence and artifacts. forge-worker pods compact Bifrost tables in the background and take no client traffic.

One binary, several roles

Every pod runs wyrd-server. WYRD_TARGET chooses what a pod does: all runs everything and is a complete deployment on its own; server, scribe, oracle, and forge-worker split API, writes, queries, and compaction so each scales on its own load. Splitting changes resource ownership, not the API: clients see one server either way. Bifrost shows which part each target runs.

One endpoint

Your load balancer owns the public address and TLS. It routes requests but never establishes who the caller is; every request carries a Wyrd token, and the server checks its roles and tenant. Pods talk to each other over mutual TLS.

Postgres and object storage

Postgres holds declarations and their versions, principals and roles, and the coordination state that lets many pods share work. Object storage holds evidence, artifacts, and Bifrost’s Parquet tables. Neither lives on a pod, which is why a pod can be lost without losing a verdict.

Identity

People sign in through your OIDC identity provider. Apps, CI, and agents use Service account keys. Identity and authorization explains principals, roles, and tenants.

Model calls

The server calls model providers with keys you configure, for model-judged checks and for apps that route their calls through the LLM gateway. Wyrd never hosts a model.

Next

How verification works follows one check through the server. Bifrost covers the data plane.

Last updated