Skip to content
View Yamini-Eshwar's full-sized avatar
🎯
Focusing
🎯
Focusing
16 followers · 13 following

Block or report Yamini-Eshwar

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
Yamini-Eshwar/README.md

banner

yamini-eshwar

Hey, I'm Yamini

AI Engineer at Aigentics Inc — I build real-time voice AI agents and avatar systems that talk to people.

I work at the intersection of conversational AI, real-time audio/video, and production infrastructure. My day-to-day involves wiring together LLMs, speech engines, and WebRTC to create AI agents that hold natural voice conversations — with lip-synced avatars, form-filling capabilities, and multi-agent orchestration.

Featured: Real-Time AI Avatar Agent

A lip-synced AI avatar that conducts voice conversations to fill out intake forms. No typing, no waiting — just talk.

Built with LiveKit (WebRTC) + Anam AI (avatar lip-sync) + Deepgram (STT/TTS) + OpenAI GPT-4o (LLM)

screen-capture.4.1.1.1.mp4

View Repo

What I work with

Voice AI & Real-Time

LiveKit Deepgram Twilio WebRTC

LLM & Agents

OpenAI LangGraph RAG Function Calling

Backend & Infrastructure

Python FastAPI TypeScript Docker Temporal Kafka Redis

Frontend

React Next.js Tailwind

Projects

Project What it does Stack
realtime-ai-avatar-agent Lip-synced avatar conducts voice intake conversations LiveKit, Anam, Deepgram, OpenAI
voice-rag-assistant Voice-enabled RAG assistant with WebRTC streaming OpenAI Agents SDK, WebRTC
snowflare-voice-support-agent Customer support voice AI with tool calling OpenAI Realtime API, WebRTC
LangGraph-Streaming-Chatbot Multi-turn streaming chatbot LangGraph, LangChain
kafka-order-tracker Real-time Kafka producer/consumer pipeline Python, Kafka, Docker

Get in touch

LinkedIn Email

yamini-eshwar

Popular repositories Loading

  1. gemini-kuki-chatbot gemini-kuki-chatbot Public

    A stylish Streamlit chatbot app powered by **Google Gemini AI**

    Python 1

  2. objectron-3d-detector objectron-3d-detector Public

    Streamlit web app for real-time 3D object detection using MediaPipe's Objectron model – supports video and image modes.

    Python 1

  3. Vehicle-Tracking-on-Highway-using-OpenCV-and-Euclidean-Distance Vehicle-Tracking-on-Highway-using-OpenCV-and-Euclidean-Distance Public

    Each object gets a unique ID and is tracked across frames on highway surveillance video.

    Python 1 1

  4. voice-rag-assistant voice-rag-assistant Public

    A real-time, voice-enabled assistant built with WebRTC and the Agents SDK that answers questions from a FAQ knowledge base using streaming agents on the OpenAI platform. Supports live speech transc…

    Python 1

  5. snowflare-voice-support-agent snowflare-voice-support-agent Public

    A realtime voice-based customer support AI assistant using OpenAI Realtime API, tool calling, WebRTC audio streaming, FAQ search integration, and ticket creation workflow.

    TypeScript 1

  6. kafka-order-tracker kafka-order-tracker Public

    Lightweight Kafka producer & consumer demo (Python + confluent-kafka) using Docker Compose — send sample orders and watch them be consumed in real time.

    Python 1