Production And Deployment

Use this page when you are moving beyond local experimentation into production architecture and rollout.

Main Concerns

Concern	Why it matters
Performance	The in-process design avoids the proxy penalty on deep agent loops
Deployment pattern	Direct SDK usage, middleware, gateway, or local providers each fit different teams
Reliability	Production rollouts need safe defaults, observability, and bounded behavior
Operations	Teams need examples for APIs, telemetry, and deployment setup