Cron Scheduled Ollama Autonomous Agent

Description and use

An hourly cron‑triggered agent uses Ollama to generate content, passes through voice, controversy, and credit gates, then publishes to channels or quarantines rejected content.

Problem

Need to autonomously generate and publish safe, relevant content to multiple channels on a schedule while ensuring compliance with voice style, controversy, and credit constraints.

Outcome

Hourly autonomous content creation with safety gates, reducing manual oversight and ensuring compliance with style, controversy, and credit limits.

Workflow

• 1. Cron triggers agent hourly
• 2. Load user voice profile JSON
• 3. Generate text with Ollama LLM
• 4. Run controversy gate via second Ollama model
• 5. Check credit gate against Postgres/Postiz
• 6. If all gates pass, publish to all channels
• 7. If any gate fails, move content to quarantine folder for review

Evidence

The agent runs on a Linux server, with a cron job triggering it every hour.

Source

The core of the agent is an Ollama model that generates text, but before any content is published, it must pass through a series of gates to ensure it's safe, relevant, and aligned with our values.

Source