Agents

Agents are the central primitive in Ren: versioned, configurable definitions that run autonomous reasoning loops. But agents don’t work alone. They compose skills for on-demand capabilities, MCPs for external tool access, and cron triggers for scheduled execution. Together, these form the capability stack that defines what an agent can do.

Agents

Versioned definitions that run.

Skills

Reusable capabilities agents compose.

MCPs

External tools via Model Context Protocol.

Cron triggers

Run agents on a schedule.