๐ Punjab โ Google, India | ๐ค AI/ML Engineer & Agentic AI Builder | ๐ Educator ยท FreeBirds Crew
From manual tester at TCS to AI/ML Engineer at Google โ no tier-1 college, no shortcuts. I build autonomous AI systems by day and teach thousands how to do it for free on YouTube by night.
-
๐ฅญ MangoOS โ Agentic AI Operating System โ Production-grade, fully self-hosted AI OS; multi-agent orchestration via LangGraph, Docker-sandboxed execution, Redis + ChromaDB memory, RBAC guardrails, and a React/Electron desktop UI โ all running locally on Ubuntu with Ollama.
-
๐ฆพ Awesome AI Agents โ 17+ autonomous agents from scratch; the most comprehensive free Agentic AI course on GitHub. 157โ
- ๐ฅ MedGemma Analyzer โ AI radiologist: high-fidelity medical imaging interpretation using MedGemma 1.5 + Streamlit
- ๐ AlphaAdvisor โ Autonomous investment strategist; real-time financial analysis + stock recommendations via Gemini + Yahoo Finance
- โ๏ธ LegalCounsel AI โ Multi-agent legal team for contract review & research; Gemini + Agno + ChromaDB
- ๐ป DevForge Agent โ End-to-end SDE assistant that plans, writes, and tests code autonomously via OpenAI Swarm
- ๐ฉบ VisionDx Agent โ Vision-based radiology assistant powered by Gemini multimodal; upload scans, get analysis
โ๏ธ NomadAI Planner โ Autonomous travel planner; custom itineraries, flights & hotels via SerpApi- ๐ง DeepSeek RAG Agent โ Fully local reasoning agent using DeepSeek-R1 + Ollama; no cloud, no cost
- ๐ฎ Gemma3 RAG Agent โ Same offline-first architecture with Google Gemma 3; privacy-first local LLM reasoning
- ๐ฅ VideoMind Agent โ Intelligent video analysis for YouTube URLs & uploads; Gemini + OpenCV
- ๐๏ธ FitCoach AI โ Personal nutrition & workout coordinator built on a multi-agent Gemini pipeline
- ๐งฌ MemoryMind Agent โ Chatbot with persistent cross-session user memory via Mem0 + Gemini
- ๐ฌ ResearchSwarm โ Deep-dive autonomous research using OpenAI Swarm multi-agent coordination
- ๐ธ๏ธ LeadHarvest Agent โ Lead generation from Quora, Amazon & job boards using Firecrawl + Composio
- ๐ AgenticRAG Flash โ Advanced PDF + web-search RAG using Gemini Flash Thinking + Exa
- ๐ญ ADK SaaS Boilerplate โ Production-ready SaaS agent scaffold on Google ADK; clone and ship
- ๐ ๏ธ ADK Toolkit โ Beginner-to-advanced Google ADK implementations collected in one place
- ๐ฆ๏ธ InfoStream Agent โ Real-time weather + news delivery agent using DuckDuckGo search tool
-
๐ Sams โ Personal OS Agent โ Karpathy-style autonomous research loop; set a goal overnight, wake up to structured Markdown reports. Docker-sandboxed, MCP-ready, adversarial AutoReason engine inside.
-
๐ NeuralForge โ Self-Extending Agent โ Agent that writes and registers its own new skills at runtime on Google ADK; full-stack (Python backend + JS frontend + dev assistant app).
-
๐ StockMarket ADK โ Production multi-agent trading system for NSE/Nifty 50; Analyst + Risk + Execution agents, SEBI 2026-compliant, Zerodha Kite integration, glassmorphism dashboard.
-
๐ฎ ARISE โ Solo Leveling AI macOS โ Gamified autonomous life-OS for macOS inspired by the Solo Leveling manga; Swift menu-bar agent powered by Gemini.
- ๐ RAG from Scratch โ LLMs โ Complete hands-on RAG curriculum: HuggingFace + LangChain + Python, zero to production.
- ๐ Pinecone RAG Pipeline โ Build end-to-end: chunking โ embeddings โ Pinecone vector store โ retrieval โ generation
- ๐งช RAG Evaluation Suite โ Measure your RAG pipeline: precision, recall, faithfulness, and context relevance
- ๐ 75DayHard GenAI Challenge โ A 75-day public learning gauntlet to master LLMs; all source code, Kaggle notebooks, and daily takeaways. 49โ
- ๐ค HuggingFace Streamlit App โ Deploy open-source HuggingFace LLMs with a Streamlit UI in under 30 minutes
- ๐ผ๏ธ ChatWithImages โ Multimodal chatbot: upload any image, ask natural language questions about it
- ๐ค NextWord Predictor โ Next-word prediction model built from scratch with deep learning fundamentals
- ๐ฌ TextToVideo PyTorch โ Generate short video clips from text prompts using PyTorch diffusion models
- ๐ฆ LLaMA 2 QLoRA Fine-Tune โ Fine-tune Meta LLaMA 2 on custom data with QLoRA; consumer GPU friendly
- ๐ฎ Dolly v2 LoRA Fine-Tune โ Instruction-tune Databricks Dolly v2 with LoRA adapters from scratch
- ๐ Phi-2 QLoRA Fine-Tune โ Fine-tune Microsoft Phi-2 with QLoRA; small model, surprisingly powerful results
- ๐ข LLaMA 3 ORPO + PEFT โ LLaMA 3 preference alignment via ORPO + LoRA + PEFT; state-of-the-art alignment technique
- ๐ธ Gemma Fine-Tune โ Domain-specific fine-tuning of Google Gemma 1.5B on custom datasets
- ๐ฌ Gemma Chatbot โ Conversational chatbot built on Gemma with full multi-turn chat history
- โ๏ธ LLM Quantization Complete Guide โ GPTQ vs AWQ vs bitsandbytes: practical comparison with benchmarks
- ๐ Quantization Deep Dive โ Binary vs integer quantization explained with hands-on experiments
- ๐ Wikipedia GPT-2 LM โ Train a language model on Wikipedia using GPT-2; understand pre-training from scratch
- ๐๏ธ Pinecone RAG (75-Day) โ Production-grade RAG with Pinecone vector DB and an LLM; challenge Day final project
- ๐ฐ LLM RAG Finance Use Cases โ Real-world GenAI + RAG applications in Finance; theory + production-grade implementations for the domain.
- ๐ Financial Analysis Python โ Financial data analysis toolkit: stock screening, portfolio metrics, and visualization in Python.
- ๐ IPL Data Analysis โ Deep EDA on IPL dataset: player stats, team trends, data profiling + visualization.
- ๐ฌ Netflix Data Analysis โ Age-rating trends, top genres, and content patterns in Netflix's 2021 catalog.
- ๐ฆ Covid-19 Data Analysis โ Impact analysis and solution mapping from global pandemic datasets.
- ๐ค ChatBot TensorFlow NLP โ Contextual chatbot using TensorFlow + NLP that understands intent and context of human language.
- ๐ Programmer Portfolio โ Personal developer portfolio: projects, skills, and source code all in one place.
- Building at Google โ designing and shipping scalable AI/ML systems in production
- Teaching on YouTube (FreeBirds Crew) โ weekly videos on Agentic AI, LLMs, RAG, and research paper explainers; always free, always project-based
- Exploring self-extending agents โ systems that write and register their own new tools at runtime
- 2026 Mission โ contribute meaningfully to the Agentic AI open-source ecosystem and help engineers across India break into AI without needing a tier-1 degree
- The DeepSeek OCR Paper Explained | AI Can Now See Text Instead of Reading
- Build 9 End-to-End GenAI Projects 2026 | RAG + Agentic AI + LLMs | Scalable System Design
- TCS to Google | From Manual Tester to ML Engineer | Punjab to FAANG | Tier 3 to GenAI
- ๐ฆพ Agentic AI โ 14 Complete Project Tutorials
- ๐๏ธ Learn RAG from Scratch with Projects
- ๐๏ธ GenAI 75 Hard Challenge + Projects
- ๐ GenAI/LLM Research Papers Explained with Maths
- AI/ML Engineer at Google โ the destination after years of relentless self-investment from a tier-3 college in Punjab
- 157+ stars on Awesome AI Agents โ the community's go-to free Agentic AI curriculum
- FreeBirds Crew โ built an active community of AI learners getting into the field without expensive courses
- Shipped 30+ open-source AI projects spanning Agentic AI, RAG, LLM fine-tuning, Finance AI, and Data Science
"Your background doesn't decide your destination โ your consistency does." I build open-source AI tools and teach for free because I needed this content when I was starting out and it didn't exist.
- Started career as a manual tester at TCS โ zero ML knowledge, zero connections
- Cracked Google without a tier-1 degree โ the long way, the real way
- Runs multiple LLM instances in parallel for research, experiments, and content
- Unwinds by drawing, playing guitar, and writing songs and poetry
- Currently obsessed with self-extending agents that write and register their own tools
- Believes the best way to master AI is to ship a project and teach it publicly


