Skip to content
View RegardV's full-sized avatar
:atom:
Building
:atom:
Building

Block or report RegardV

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
RegardV/README.md

Building Production AI Systems That Run in My Garage

AI Workflow Engineer | Shipping autonomous content factories & agentic dev teams on sovereign infrastructure


🚀 What I Ship

Shorts Factory – Autonomous Content Engine

70+ videos live across YouTube, Instagram, TikTok, X with zero manual intervention

Production System (Live Now):

  • 85-90% local inference – no API dependency hell
  • Full pipeline: n8n → ComfyUI → Remotion → Chatterbox-TTS → Postiz
  • Running 24/7 from Pretoria on Xeon E3 + RTX 3090

→ [Personal Dashboard](Personal Development Roadmap) (Business hours GMT+2)

Business Impact: Scaled content production from 0 to 70+ pieces while eliminating $500+/month in API costs


Claude Autonomous Coding Team – Zero-Cloud Dev Squad

Senior-level development pipeline with zero external dependencies:

  • OpenSpec enforcement for consistency
  • Automated drift detection & PR-Agent reviews
  • Human-in-the-loop gates for critical decisions
  • Single script deployment

Impact: What took 3 days now takes 3 hours. Code quality improved, human bottlenecks eliminated.


CrewAI Production Systems

  • 30-Day PDF Journal Generator: CLI shipped, frontend 85% complete
  • Hummingbot Trading Manager: Autonomous trading orchestration
  • Family Finance Tracker: Bank statement parsing + budget automation

🎯 What I Solve

The Problem: Companies want AI agents but can't afford the cloud bills, data leakage risks, or API rate limits.

My Solution: Production-grade agentic systems that run locally, privately, and profitably.

  • Sovereignty: Your data never leaves your infrastructure
  • Cost Control: 85-90% local = 90% cost reduction vs. cloud APIs
  • Compliance: POPIA/GDPR-ready by default
  • Reliability: No rate limits, no API downtime

🛠️ Production Stack

Daily Operations:

Docker • n8n • ComfyUI • Remotion • Chatterbox-TTS • Postiz  
Nginx • Postgres • Redis • Claude API (10% of workload)

Hardware: Xeon E3 • 64GB RAM • RTX 3090 (all running from Pretoria)

Expertise:

  • Agentic Workflows & Multi-Agent Orchestration
  • LLMOps & Prompt Engineering (ReAct, Reflexion, ToT, PAL)
  • Local/Sovereign AI Architecture
  • Cost Optimization & Compliance Engineering

📈 Track Record

  • Jan 2025: Zero AI experience
  • Dec 2025: Shipping 70+ autonomous content pieces, running multi-agent dev teams, building CrewAI production systems

Speed matters. Results matter more.


🤝 What I'm Looking For

Open to collaborations on:

  • Production-grade agentic systems
  • Privacy-first AI infrastructure
  • Autonomous workflow automation
  • Ethical AI that actually respects data sovereignty

Ideal fit: Fast-moving teams solving hard problems that require local inference, cost control, and zero compromise on privacy.


📍 Location & Context

Based in Pretoria, South Africa (yes, same city as Elon – the coincidence keeps me ambitious).

Running production AI systems from my garage. Proving you don't need SF rent or cloud budgets to ship world-class AI.


📫 Let's Build

If you're tackling problems where data sovereignty, cost control, and production reliability aren't negotiable – let's talk.

Realandworks.com[Linked-In]


Status: Open to challenging projects | Prefer: High-impact, fast-moving teams | Remote-first

Pinned Loading

  1. rtx-gpu-memory-manager rtx-gpu-memory-manager Public

    Professional-grade GPU memory management system for RTX 30/40 series GPUs with intelligent automation, thermal protection, and comprehensive monitoring

    Shell

  2. Enhanced-Markdown-to-PDF Enhanced-Markdown-to-PDF Public

    a Professional PDF from Markdown

    Shell