| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Original HTTPS Page] |
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.
Contact GitHub support about this userβs behavior. Learn more about reporting abuse.
Report abuseI'm a Full-Stack Developer & AI Engineer from India specializing in the MERN Stack and building intelligent systems. I work on RAG pipelines, Agentic AI architectures, and LLM evaluation & gateways β combining full-stack development with deep AI/ML expertise.
|
MCP Orchestrator β Selected project for Swiggy Builders Club. An orchestration & routing layer for Model Context Protocol (MCP) servers β enabling agents to dynamically discover, compose, and call MCP tools across the Swiggy ecosystem (food ordering, Instamart, Dineout, Genie). |
| Project | Description |
|---|---|
| MCP-SERVER | Model Context Protocol server implementation β exposes tools/resources to LLM agents via the MCP spec. Foundation for the Swiggy Builders Club MCP Orchestrator work. |
| Langchain-MCP | LangChain β MCP integration β lets LangChain agents discover and call any MCP-exposed tool seamlessly. |
| LangGraph-Ai-Agent | Stateful, graph-based agentic AI workflows built with LangGraph β multi-step reasoning, branching, and human-in-the-loop. |
| LangChain-ai-agent | ReAct-style AI agent built on LangChain β tool use, retrieval, and chain-of-thought orchestration. |
| Guardrails | Output validation & safety guardrails for LLM responses β schema enforcement, content filtering, and policy checks. |
| LLM-products | Collection of LLM-powered product features β RAG, summarization, and conversational UI patterns ready to ship. |
π₯ Swiggy Builders Club β Selected (2026) Approved to build MCP Orchestrator on Swiggy's MCP platform. building live at mcp.swiggy.com/builders.
π₯ AMD Slingshot 2026 β Finalist (Hyderabad) Built an AI solution for AI in Consumer Experience; selected as a finalist among teams nationwide.
π€ RAG Agentic AI System β designed and shipped a retrieval-augmented agentic pipeline with multi-tool orchestration.
π§ LLM Evaluation & Gateways β building evaluation harnesses and inference gateways for safe, observable, and production-grade LLM deployments.
Pluggable orchestration layer across multiple MCP servers with context-aware task prioritization
Enterprise LLM & RAG Evaluation Suite using LangSmith observability and LLM-as-a-Judge grading to benchmark chatbots and Retrieval-Augmented Generation pipelines across Google Gemini, Groq (Llama 3β¦
Jupyter Notebook 1
Enterprise LLM gateway built with LiteLLM & LangChain. Decouples client workflows from model endpoints with load balancing, caching, automatic fallbacks, and safety guardrails.
Jupyter Notebook 1
production-ready workspace demonstrating agentic design patterns using the DeepAgents (LangGraph) harness, Groq Llama, and Tavily search.
Jupyter Notebook 1
A healthcare AI project demonstrating guardrails for safe and responsible agent-based interactions using LangChain, LangGraph, and Groq.
Jupyter Notebook 1
| Back | FazBrowse Home | New Git URL |