AI agent engineer · Vadodara, India · portfolio
I build AI agent products end to end at Gradscaler — from the first conversation with a client to the thing that runs in front of their users. I got here the long way: WordPress, then Flutter, then backends, then agents.
| Project | What it does | |
|---|---|---|
| Mediator Gabby | Separating parents each talk things through alone with the agent, in their own private room. Once both are done it lines the answers up — agreed, partly, not yet — and hands that to their mediator. Thirteen topics, two scoped rooms, LangGraph and FastAPI underneath. | in production · private |
| remotion-video-mcp | Gives Claude a video editor. Describe what you want and it scaffolds the Remotion project, writes the scenes, syncs narration to the words and renders the MP4. Thirteen tools, no timeline to drag. | public · MIT |
| Hundi | Your salary lands, you confirm it, and it splits by percentage into buckets — savings and investments first, expenses get what's left. No bank linking, nothing logged behind your back. | in beta · private |
| Maya | A voice agent that lives on my Linux home server and never phones home. Ollama takes the GPU, Whisper and Piper stay on CPU. Read-only by design — it can tell you about the server, never change it. | fits in 4 GB VRAM |
Every step above started as something I taught myself on the side, and the working out is public. These are the repos where I actually learn things — commits from the days I hadn't understood it yet, not a tidy write-up after the fact.
| Repo | What's in it |
|---|---|
| LangGraph_Learning | Multi-agent workflows, tool-calling, and stateful AI systems |
| LangChain-Learning | RAG pipelines, chains, memory, and LLM integrations |
| Agno-Learning | The current one — working through Agno to see what it does better |
| neural_network_learning | Neural nets from scratch — micrograd, makemore, backprop |
What I reach for by default. The list is short on purpose.
Building things that think.