Welcome to my blog — a digital lab notebook where I share my learnings, experiments, and reflections at the intersection of Generative AI, System Design, and Human-AI Collaboration.
🚀 What I’m Working On
🧠 Naval-Gemma
A fine-tuned Gemma-3B model trained on The Almanack of Naval Ravikant for philosophical Q&A.
→ Hugging Face • Ollama Demo
📔 Echo
An AI-powered journal that uses RAG, embeddings, and feedback loops to evolve with your thoughts.
→ GitHub
🔗 Orchnex
A framework to orchestrate multiple LLMs like Gemini, LLaMA, and more — optimizing for reasoning accuracy.
→ GitHub
🔥 Phoenix
A voice-enabled, multimodal assistant with wake-word, RAG, Whisper, and custom function calling.
→ GitHub
🧩 Open Source Contributions
- 🐝 Swarms: Multi-agent LLM coordination with UI/UX and plug-and-play RAG API module.
- 💡 RAG REST services for payload-only integration.
- 🎨 Gradio-powered interface improvements.
📚 Why This Blog Exists
I’m currently a second-year undergrad focused on building:
- Human-aligned AI systems
- Fast, explainable, and voice-friendly interfaces
- Developer tools to accelerate innovation
This blog will be home to:
- ✍️ Technical breakdowns of my projects
- 🎯 Weekly goals & build-in-public posts
- 🧪 Lessons from failed and successful experiments
- 🛠️ Infrastructure, productivity, and life as a solo builder
🧭 Let’s Connect
“I don’t just want to build AI—I want to build the future where AI works with us, not just for us.”
Thanks for stopping by. New posts drop frequently. 🧵