npx --registry=https://registry.npmjs.org @modelcontextprotocol/inspector
AI tools built into the Findipend platform — multi-agent research workflows and technical-indicator pipelines that power the portfolio's signal generation.
A LangGraph supervisor runs five parallel sub-agents (on-chain, tokenomics, sentiment, technical, fundamental) into one composite-scored report. Runs on Anthropic, OpenAI, Google, or Ollama.
Computes 20+ technical indicators, and combines sentiment signals into a single decision score. It outputs a clear buy/hold/sell recommendation with interactive charts and locally stored run history
The following case studies highlight standalone machine learning projects, demonstrating data science and AI applications completely separate from the Findipend portfolio.
Clears your inbox, sends emails, manages your calendar, checks you in for flights. All from WhatsApp, Telegram, or any chat app you already use.
A custom CV generator tailored to job descriptions based on your work experience.
A comprehensive analysis of employee attrition to help HR departments proactively identify flight risks and understand key drivers of turnover.
A machine learning approach for analyzing Spotify song data to build cohort-based recommendations and explore musical feature patterns.
An end-to-end TensorFlow CNN trained on 120 dog breeds from the Kaggle dataset, capable of identifying any breed from a single photo.
A PyTorch-based CNN image classifier that identifies clothing items across 10 Fashion-MNIST classes: T-shirt/top, Trouser, Pullover, Dress, Coat, Sandal, Shirt, Sneaker, Bag, and Ankle boot.