Skip to content
View NayanKanaparthi's full-sized avatar
12 followers · 13 following

Achievements

Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Pull Shark

Highlights

  • Pro

Organizations

@AdvantageCommunity

Block or report NayanKanaparthi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
NayanKanaparthi/README.md

Hi, I'm Nayan 👋

I build AI systems and try to figure out how to get people to actually use them. Most AI projects fail at adoption, not at the technology, and that's the gap I find interesting.

I work mostly in Python and TypeScript. Lately that means RAG pipelines, multi-agent systems, fine-tuning small open-weight models with QLoRA, semantic caching, and shipping CLI tools and developer tooling. I care about governance and reliability as much as I care about the model layer, which is probably why I keep ending up writing guardrail registers and OWASP mappings instead of chasing the newest benchmark.

📬 nk4286@stern.nyu.edu
🔗 linkedin.com/in/nayan-kanaparthi
🌐 nayankanaparthi.dev

Pinned Loading

  1. aigis aigis Public

    AI governance guardrails for coding agents. Curated security and compliance patterns from NIST AI RMF, OWASP Top 10 for LLMs, and ISO/IEC 42001.

    JavaScript 4

  2. deepscout-research-agent deepscout-research-agent Public

    DeepScout is a fully optimized small-model research agent that distills frontier-level web reasoning into deployable 3B models using QLoRA, post-training quantization, and vLLM serving — powering a…

    Python 1

  3. Tokenomics-AI/Tokenomics Tokenomics-AI/Tokenomics Public

    Make every token count — an experimental LLM inference layer that optimizes cost through caching, adaptive routing, and ML-assisted decision-making.

    Python 2

  4. Veritas-RAG Veritas-RAG Public

    A portable, local-first RAG retrieval engine that packages your knowledge into a shippable “retrieval artifact” for fast, offline, privacy-preserving search (no vector DB, no server).

    Python

  5. risk-lab risk-lab Public

    Quantitative risk and stress testing simulator using Monte Carlo and factor models, built with Python and Streamlit to analyze portfolio resilience under real-world market scenarios.

    Python

  6. yaojiejia/anticipate yaojiejia/anticipate Public

    TypeScript 2 2