Skip to content
View sohom2004's full-sized avatar
🎯
Focusing
🎯
Focusing
9 followers · 6 following

Block or report sohom2004

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
sohom2004/README.md

Hi 👋, I'm Sohom Roy

🚀 Building Agentic AI Systems | Full-Stack Developer | Future Cloud Engineer

🧠 About Me

  • 🔥 Building Agentic AI systems with MCP architecture
  • ⚙️ Full-stack dev: React + Node + Django
  • ☁️ Working towards becoming a Cloud Engineer
  • 📚 Strong focus on system design + real-world AI deployment

🛠️ Tech Stack

🚀 Current Work

  • 🧩 Multi-agent AI frameworks (Planner → Executor → Reflector)
  • 🏥 MedInsight (AI medical assistant system)
  • 🤖 Automation workflows (Make.com + AI agents)

📊 GitHub Stats

📈 Activity Graph

🐍 Contribution Snake (Animated)

🚀 Featured Projects

🔹 MedInsight

  • Multi-agent orchestration based medical report longitudinal analysis, specialist recommendation and context-based querying
  • Complete ready-to-deploy software

🔹 ScrapedIn

  • Multi-agent orchestration based LinkedIn lead genration tool
  • Automated web scraping and regular expression based information extraction

🔹 RAG Based Document QnA Tool

  • Retrieval Augmented Generation based tool
  • Upload and query your documents

🌐 Connect With Me

👀 Profile Views

⚡ Philosophy

I don’t just build software — I design systems that think, adapt, and evolve.

Pinned Loading

  1. ScrapedIn-Agentic-LinkedIn-Scraper- ScrapedIn-Agentic-LinkedIn-Scraper- Public

    Built an agentic linkedIn lead scraper that performs query based google search, fetches profiles and scrapes necessary information like user name, position, about, email and the profile url

    Python 4

  2. RAG_QnA RAG_QnA Public

    convert your text/pdf to markdown and upload them to the database then ask any question from the text and get top 5 responses along with their metadata like page number, etc..

    Python

  3. AMS_project AMS_project Public

    Attendance Management System with face recognition

    JavaScript 1