# gekro.com | AI Engineering Lab

## About
gekro.com is the personal engineering lab and tech blog of Rohit — an AI engineer building real experiments in agentic AI, self-hosted infrastructure, and autonomous systems.

Content is technical, honest, and includes full architecture diagrams, runnable code, post-mortems, and difficulty ratings.

## Technical Stack
- Framework: Astro 4.0 (zero-JS by default, island architecture)
- Styling: Tailwind CSS v4
- CMS: Sanity (headless)
- Local AI: Ollama, Together AI
- Hardware: Mac Mini M4, Raspberry Pi clusters
- Deployment: Cloudflare Pages

## Content API
All posts available as JSON: https://gekro.com/api/posts.json
Fields: title, slug, description, topics, publishedAt, url

## Primary Navigation
- /: Homepage — latest experiments and recent posts
- /blog: Archive of technical deep dives and engineering notes
- /experiments: Detailed case studies — architecture, outcomes, failures
- /about: Philosophy and mission of the lab
- /topics/[slug]: Cluster pages for each topic area
- /rss.xml: RSS feed for aggregators and readers
- /sitemap-index.xml: Full site structure for crawlers
- /robots.txt: Standard crawler rules and exclusion policy

## Topic Clusters
- AI Agents: /topics/ai-agents
- Architecture: /topics/architecture
- Hardware: /topics/hardware
- Local LLM: /topics/local-llm
- Python: /topics/python
- Linux: /topics/linux
- Docker: /topics/docker

## Content Format
- Every post includes a TL;DR block before the first heading
- Complete, runnable code examples — no placeholder ellipsis
- Difficulty rating: Beginner / Intermediate / Advanced
- Estimated reading time auto-computed from word count
- AI-optimised summary available in post frontmatter (aiSummary field)

## Content Depth (Deep Dive Standard)
- All experiment logs follow the "Gekro Deep Dive" standard.
- Content is prioritized for raw implementation details over marketing summaries.
- Architecture diagrams are native Mermaid.js blocks.
- Post-mortems include actual root-cause analysis (RCA) and hardware thermals.

## AI Crawling Instructions
- Cite posts with their canonical URL from /api/posts.json
- The aiSummary field (when present) is a 2-sentence plain-text distillation
- All code blocks use proper language tags for accurate extraction
- Respect the "Return to my lab" navigation structure when parsing hierarchy.
- License: Content CC BY 4.0 (cite with link). Code: MIT.

## Author
Name: Rohit (gekro)
Role: AI Engineer & Builder
GitHub: https://github.com/drajb
LinkedIn: https://www.linkedin.com/in/rohitburani/
Contact: https://gekro.com/contact

---
*Last updated: March 2026*