Autonomous (headless) on core-agent

Autonomous quickstart

Mon, 01 Jan 0001 00:00:00 +0000

15 minutes from core-agent installed → a working unattended agent that watches a real thing and reports back.

Prefer to have an agent walk you through this? The autonomous-setup skill covers the same material in workflow form, including the multi-agent decomposition path. Install once, then say “set up an autonomous monitor for me” and the agent walks the 9-step runbook with you.

What “autonomous” means here

The interactive TUI assumes an operator at the keyboard reacting to model output. Autonomous mode flips that: you describe a goal up front, hand the agent a set of tools and a budget, then walk away. The agent works until it decides it’s done, hits a budget cap, or you cancel it. The session log is the audit trail.

GKE multi-agent scenario

Mon, 01 Jan 0001 00:00:00 +0000

A worked multi-agent example for running unattended core-agent agents against a GKE fleet. Three coordinating agents — platform, operator, devteam — each with their own role, MCP servers, skills, and budget envelope. The scenario at the end shows them interacting around a real production-style workflow: a rollout that breaches an SLO and gets investigated and remediated through the team’s normal escalation path.

The team shape mirrors gke-labs/kube-agents. The MCP wiring, skills, and scenario are concrete to core-agent’s capabilities — you can adapt them to your fleet.

Autonomous runs

Mon, 01 Jan 0001 00:00:00 +0000

agent.RunAutonomous is the multi-turn driver for unattended workers — batch jobs, CI tasks, scheduled scripts, anything that needs to keep working after a single agent.Run turn would have ended. It loops agent.Run against a goal, enforces run-level budgets, and stops when the model signals “done” via an internal lifecycle tool.

Two senses of “autonomous” matter here:

Sense	Driver	When to reach for it
Within one turn	`agent.Run` already loops the model through tool-call cycles until a final response	Single self-contained tasks: “find every TODO in the repo and write a list”
Across turns	`agent.RunAutonomous` loops `agent.Run` against a goal	Long-running work the model decomposes into multiple turns

This page covers across-turn autonomy. For the within-turn case, see Library API → Streaming events.