Skip to content
View anshupriyan's full-sized avatar
  • New Delhi India
  • 11:39 (UTC -12:00)

Highlights

  • Pro

Block or report anshupriyan

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
anshupriyan/README.md

Priyanshu Raj

AI • Systems • Security • Open Source

Second-Year B.Sc. Computer Science Student @ University of Delhi

Building local AI infrastructure, developer tools, and security research.

GitHub Analytics

Typing SVG

About

I'm a second-year Computer Science student passionate about Artificial Intelligence, Systems Programming, Cybersecurity, and Developer Tools.

I enjoy learning by building—from local LLM infrastructure and AI automation to reinforcement learning, hardware security, and post-quantum cryptography.

Highlights

  • 3rd Place — ISEA Hardware Security Innovation Challenge, IIT Kanpur
  • Participant — AMD × Unsloth Reinforcement Learning Hackathon, IIT Delhi
  • Built VaultMind — MCP-powered AI memory infrastructure connecting Claude Desktop with Obsidian.
  • Built BrainSync — Local LLM-powered semantic knowledge management for AI conversations.
  • Built DisCap — Low-latency Windows ↔ Android display streaming with GPU acceleration.
  • Implemented a Correlation Power Analysis attack on CRYSTALS-Kyber (ML-KEM).

Tech Stack

Languages

AI / Machine Learning

Frameworks & Libraries

TransformersTRLHugging FaceUnslothGRPOSFTOllamaMCP

Development

Activity

Building in Public • Open Source • Research • Always Learning

Pinned Loading

  1. BrainSync BrainSync Public

    Sync & tag your ChatGPT/Claude exports into Obsidian using a local LLM. No cloud, no API keys.

    Python 10

  2. AI-Examiner-Reinforcemnt_learning-fine_tunning AI-Examiner-Reinforcemnt_learning-fine_tunning Public

    Adversarial LLM arena using GRPO + SFT to train a model that generates questions hard LLMs can't solve

    Python 9

  3. My-CPA-code-analysis My-CPA-code-analysis Public

    Correlation Power Analysis on CRYSTALS-Kyber (ML-KEM) — IIT Kanpur Hardware Security Challenge

    Python 11