Runtime Status Matrix
This page is sourced from the monorepo and is not available in this build.
Skills vs Tools vs Extensions
Which capability system to reach for when. The decision is rarely ambiguous if you know what each one actually owns — this page is a verified-against-the-source map of the three.
Observability (OpenTelemetry)
You can't operate an agent runtime in production without observability, and the cost of bolting it on after the fact is paid in incidents you can't reproduce. AgentOS treats spans, metrics, and log correlation as first-class concerns — but it does not own the OpenTelemetry SDK lifecycle. The SDK is an application-level concern: your host owns exporters, sampling, and context propagation, because the right answer for a CLI process is different from the right answer for a long-running server is different from the right answer for an edge worker.
Logging (Pino + OpenTelemetry)
AgentOS uses structured JSON logs via pino and supports opt-in OpenTelemetry (OTEL) correlation and export.
LLM Providers
The cost of a model going down today does not save you when it goes down tomorrow. The right question for any production agent runtime is not which provider — it is what happens when this provider isn't available. Provider outages happen. Rate limits hit at the worst moment. A model deprecates. A region throttles. A subscription lapses. None of these stop being true because the agent is mid-conversation.
Streaming Semantics
AgentOS now exposes multiple streaming surfaces on agency().stream(...) because
OAuth Auth
The @framers/agentos/auth subpath export provides OAuth authentication primitives for LLM providers. It implements the device code flow for obtaining API access tokens from consumer subscriptions.