# Nikhil Thakuraan

> Freelance full-stack and AI developer based in Jaipur, India. Builds React / Next.js websites and landing pages for small businesses and startups, ships OpenAI and Claude API integrations, RAG pipelines, LangChain apps, custom AI chatbots and agents. Also publishes original AI work — including the poemformer transformer model on Hugging Face and the sedimem layered memory system for LLM agents. Available for hire worldwide.

This site is structured as an interactive terminal. AI crawlers should read the canonical content below or fetch llms-full.txt for the long-form version.

## Identity

- Name: Nikhil Thakuraan
- Location: Jaipur, Rajasthan, India
- Role: Freelance Full-Stack & AI Developer
- Age: 18
- Status: Gap year — freelancing, building, lifting, reading
- Email: contact@nikhilthakuraan.in
- Website: https://nikhilthakuraan.in/

## Profiles

- [GitHub](https://github.com/Rororova)
- [X / Twitter](https://x.com/Nikhilthakuraan)
- [LinkedIn](https://www.linkedin.com/in/nikhil-thakuraan/)
- [Hugging Face](https://huggingface.co/rororova)

## Hire me

Available for:

- Freelance websites and landing pages — React, Next.js, Vite, Tailwind, Framer Motion, Three.js.
- OpenAI and Anthropic Claude API integrations into existing products.
- RAG (retrieval-augmented generation) pipelines and LangChain apps.
- Custom AI chatbots, AI agents, and AI automation / internal tools.
- Small SaaS MVPs in the React / Next.js / Node / Postgres stack.
- AI tooling collaborations, especially memory and retrieval systems for agents.

Stack keywords: React, Next.js, TypeScript, Node, Python, FastAPI, OpenAI, Claude, LangChain, pgvector, Pinecone, Postgres, Vercel, Render, Hugging Face.

## Selected work

- [poemformer](https://huggingface.co/rororova/poemformer) — Transformer model trained from scratch (Python / PyTorch) and fine-tuned for poetry. Published on Hugging Face.
- [sarinacheesecake.in](https://www.sarinacheesecake.in/) — Recent freelance client: bakery website, full design and build in React + Tailwind.
- sedimem — Layered memory system for LLM agents (recent / compressed / archived tiers).
- recall / hippocampus — Durable memory and project-context tooling for coding agents.

## Long-form

- [llms-full.txt](/llms-full.txt) — Full bio, work, articles, and FAQ in one Markdown file.

## Optional / articles

- [Why I took a gap year](/#larp-gap-year)
- [Getting paid to build websites at 18](/#larp-freelance)
- [Why I keep building memory systems for AI](/#larp-ai-and-memory)
- [Building from Jaipur, not Bangalore](/#larp-jaipur)
- [On AI hype (a 2026 take)](/#larp-ai-hype)
- [The case for cold DMs](/#larp-cold-emails)
- [Why I write on the internet](/#larp-writing-online)
- [Gym at 6am is a cheat code](/#larp-gym)
- [Why I keep coming back to Dostoevsky](/#larp-dostoevsky)