Skip to content
View Abdur-Rafay-AR's full-sized avatar
20 followers · 18 following

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Quickdraw

Highlights

  • Pro

Block or report Abdur-Rafay-AR

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.

Content in all repositories owned by your account will be closed.
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
Abdur-Rafay-AR/README.md

Abdur Rafay

AI/ML Engineer building production-grade agentic systems

RAG pipelines, multi-agent systems, and voice AI in production

Background

AI/ML engineer pursuing a Bachelor's in Artificial Intelligence, currently working in Cloud Operations at Lythe Labs. Shipped 25+ production AI systems spanning RAG pipelines, multi-agent orchestration, and voice agents, backed by six internships across international teams. Open to select freelance or contract work.

Stack

Languages Python TypeScript

AI / Agents Groq LangChain RAG

Backend & Real-time FastAPI WebSocket SQLite

Frontend & Infra React Docker AWS

Certifications

IBM AI Developer Professional Certificate

More on Credly →

Featured work

Open-source tooling built at Lythe Labs, co-built with the team.

Project What it does Stack
voice-agent-starter-kit Real-time voice agent template: streaming ASR → LLM → TTS pipeline over WebSocket, feels like an actual phone call Python, FastAPI, WebSocket
autonomous-agent Long-running autonomous agent with persistent memory, sandboxed code execution, and a resumable control-plane API Python, FastAPI, SQLite, React
agent-testing-suite Local-first observability and evaluation framework for AI agents: execution tracing, live dashboard, multi-model support TypeScript, Next.js
ai-cache Automatic caching layer for LLM API responses across OpenAI, Gemini, and Anthropic Python, LLM APIs

📊 GitHub Stats:

Top Languages      GitHub Activity

Pinned Loading

  1. crucible crucible Public

    Multi-agent collaboration engine with persistent, searchable, self-compacting memory. Agents research, critique and adjudicate over a shared SQLite memory with hybrid BM25 + embedding recall. Zero-…

    Python 2

  2. lythelab/voice-agent-starter-kit lythelab/voice-agent-starter-kit Public

    A production-ready voice agent template that feels like a real phone call

    Python 8 1

  3. ai-cache ai-cache Public

    Transparent, cost-aware caching for LLM API responses. Cut spend and latency on repeated OpenAI, Anthropic, and Gemini calls without changing your code.

    Python 1

  4. bahria-LMS-assignment-checker bahria-LMS-assignment-checker Public

    This repo is my work to automate the bahria lms to check for assignments.

    Python 3 1

  5. heart-attack-risk-analysis heart-attack-risk-analysis Public

    A comprehensive web application for analyzing heart attack risk factors using Python and Flask. Features interactive data visualizations, statistical insights powered by NumPy and Pandas, and a

    Python

  6. stock-market-predictor stock-market-predictor Public

    Stock price prediction app using Streamlit and PyTorch LSTM, featuring real-time data from Yahoo Finance, customizable inputs, and interactive visualizations.

    Python