/v1/chat/completions and /v1/models endpoints, so existing SDKs work unchanged.
Decision layers
ROUTER routes requests across several parallel decision layers. The routing result (layer, decision, model) comes back in response headers:Routing config (YAML v0.3)
You declare entrypoints, providers, and routing rules in a YAML v0.3 config that ROUTER reloads dynamically. The config blocks:Gold entrypoints
Common virtual entrypoints ship with built-in recipes:ariacompute/semantic-autoariacompute/agent-autoariacompute/afm-d-auto
AFM_ENGINE_URL pointing at a running aria-engine. The layer and decision come back in x-aria-router-* response headers.
Constraints and governance
Shared provider models and hard constraints (cost, latency, capability) are evaluated at request time. The management plane covers authentication, routing configuration, cost tracking, and key management under/v1/router/*; AFM_ENGINE_URL can wire afm-d into System One.
How to run
- ROUTER Runtime — self-host
aria-routerCLI / FFI; data plane defaults to--bind 127.0.0.1:8899, management plane--mgmt-bind 127.0.0.1:8090. - AGENT Runtime — for tool use and planning scaffolding only, see
aria-agent. - Related: ROUTER introduction, AFM foundation models.