Skip to content
View Ritesh90256's full-sized avatar
🎯
Focusing
🎯
Focusing
1 follower · 0 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report Ritesh90256

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
Ritesh90256/README.md

Hi 👋, I'm Ritesh Minchinal

Developer from Bangalore, India

AI

🚀 About Me

  • 🛡️ Building Vigil, an open-source observability platform that automatically diagnoses why AI agents fail in production
  • 🤖 Building Agentic AI systems using CrewAI, LangGraph, AutoGen and OpenAI Agents SDK
  • 🧠 Passionate about multi-agent workflows, autonomous systems and AI automation
  • 🧬 Exploring digital twins & human physiology simulation — bridging AI with biomedical modelling
  • 🎓 3rd Year CSE student at PES University, Bangalore
  • 🏆 Top 10 in Nationwide Gen AI Challenge by Great Learning
  • 💬 Ask me about AI Agents, Reinforcement Learning, Digital Twins, Multi-Robot Systems
  • 📫 Reach me at riteshminchinal365@gmail.com
  • 🌐 Portfolio: ritesh90256.github.io/portfolio
  • ⚡ Fun fact: I Love playing Sports

🔗 Connect With Me

LinkedIn GitHub Email Portfolio

🛠️ Tech Stack

Agentic AI

CrewAI LangGraph AutoGen OpenAI HuggingFace

AI & Machine Learning

Python PyTorch TensorFlow Gymnasium

Backend & Infra

FastAPI PostgreSQL Docker AWS

Simulation & Visualisation

Unity NumPy BioGears

Languages & Tools

C C++ Java Git VS Code Google Colab

📊 GitHub Stats

🏆 Featured Projects

Project Description Tech
🛡️ Vigil Actively building. Open-source observability platform that captures every LLM call & tool use from an AI agent and auto-classifies failures (hallucination, tool misuse, infinite loops, prompt injection, and more) Python, FastAPI, PostgreSQL, LLM-as-Judge
Astronaut Fatigue Digital Twin Digital twin simulating astronaut fatigue & sleep deprivation over a 30-day space mission with Monte Carlo analysis BioGears, Python, Unity 3D
Multi-Robot Task Allocation Autonomous robots using CBBA, RVO2 and A* — implemented from scratch Python, Pygame, NumPy
Pac-Man Deep Q-Learning DQN agent trained to play Ms. Pac-Man with experience replay and target networks PyTorch, Gymnasium
KungFu A3C Agent A3C agent with parallel environments and shared network to play KungFu Master PyTorch, Gymnasium
Lunar Lander DQN DQN agent solving LunarLander-v3 with experience replay PyTorch, Google Colab

🎖️ Achievements

  • 🥇 Top 10 in Nationwide Gen AI Challenge — Great Learning
  • 🏅 2x Distinction Award — PES University

Pinned Loading

  1. kungfu-a3c-agent kungfu-a3c-agent Public

    A3C-style parallel actor-critic agent trained to play Kung Fu Master (Atari) using PyTorch and Gymnasium. Includes parallel environments, shared network, and video playback.

    Python

  2. lunar-lander-dqn-agent lunar-lander-dqn-agent Public

    Deep Q-Learning agent for OpenAI LunarLander-v3 environment.

    Python

  3. multi-robot-task-allocation multi-robot-task-allocation Public

    2D simulation of multi-robot task allocation using CBBA, RVO2 and A* — built from scratch in Python

    Python

  4. pacman-deepq-learning pacman-deepq-learning Public

    Deep Q-Learning agent trained to play Ms. Pac-Man using a convolutional neural network and experience replay. Built with PyTorch and Gymnasium.

    Python

  5. astronaut-fatigue-digital-twin astronaut-fatigue-digital-twin Public

    A digital twin of an astronaut simulating fatigue and sleep deprivation over a 30-day space mission, integrating BioGears human physiology engine, Python simulation, Monte Carlo analysis, and Unity…

    Python