Skip to content
View Ekansh1605's full-sized avatar

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report Ekansh1605

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
Ekansh1605/README.md

Hi, I'm Ekansh

📍 Bonn, Germany · 🎓 M.Sc. Computer Science @ Universität Bonn · 🤖 LLM & agentic AI systems

Building

  • Lastenheft - Multimodal RAG over German/English industrial PDFs, with a LoRA-fine-tuned reranker, a LangGraph multi-agent pipeline, and EU AI Act compliance.

  • kaffeeundkuchen-claw - Terminal AI coding agent (TypeScript/Bun) with sandboxed file operations and a human-in-the-loop diff approval flow.

Projects

  • yumo - First technical hire: built the product end to end with a multi-agent workflow and RAG pipeline (Next.js, Supabase, n8n) that cut a multi-day manual process to minutes. (working student)

  • Autonomous Perception Pipeline - Multi-task video understanding on CARLA data: semantic segmentation, monocular depth, and ego-motion in PyTorch.

  • InsightPDF - Conversational RAG for multi-turn PDF question answering with LangChain and ChromaDB.

Tech

Python · TypeScript · PyTorch · Hugging Face · LangChain · LangGraph · FastAPI · Next.js · PostgreSQL / pgvector · Docker

GitHub activity

GitHub activity graph

linkedin · portfolio · email

Pinned Loading

  1. Lastenheft Lastenheft Public

    Sovereign multimodal RAG for German industrial documentation. EU AI Act-aware by design. Built with ColQwen2/ColPali, LangGraph, FastAPI, Next.js, pgvector.

    Python

  2. Video_Segmentation_and_Understanding_Automotive_Scene Video_Segmentation_and_Understanding_Automotive_Scene Public

    Jupyter Notebook

  3. KaffeundKuchen-claw KaffeundKuchen-claw Public

    Build your own clawbot.

    TypeScript

  4. Distracted-Driver-Detection Distracted-Driver-Detection Public

    Problem statement: Given the dataset consisting of driver images in car and corresponding labels for 10 nos. categories (e.g. safe driving, texting, talking etc.), My task is to build a classificat…

    Jupyter Notebook