Lyall Paldano
CV
© 2026 Lyall Paldano. All rights reserved.
Back to Home

YouTube AI Content Agent

Jun 2025 - Sep 2025

Self-hosted n8n agent that researches trending topics daily, generates niche-specific video scripts via Google Gemini, and runs an AI Judge layer for quality control. The predecessor to OpenClaw.

Tech Stack
n8nJavaScriptDockerDocker ComposeLinux VPSGoogle Gemini APIGoogle Custom SearchOllama

Challenge

Manual trend research and creative writing is a daily bottleneck for content channels. I wanted a set-and-forget agent that produces production-ready scripts every day on a 1GB RAM VPS, so the unit economics worked.

Solution

Built a self-hosted n8n v2.0 workflow on a Linux VPS with Docker Compose. After an initial attempt to run Llama 3.2 locally OOM-crashed the box, I diagnosed the bottleneck via terminal resource monitoring and pivoted to a hybrid architecture: keep logic local, offload inference to Google Gemini. Refactored the entire pipeline from file-based to a RAM-only JSON object passing model after hitting EACCES errors on Docker volumes. Added a secondary AI Judge workflow to gate output for safety and relevance.

Outcome

Daily generation pipeline running with parent/child workflow separation between scraper and generator. Cut potential server-upgrade costs by 400% and lifted generation speed 10x by going hybrid cloud. The architecture I worked out here grew into OpenClaw.

Skills Learned

Workflow orchestration under hardware constraintsParent and child workflow architectureLinux administration and Docker permissionsPrompt engineering with strict JSON outputHybrid cloud cost engineering