Skip to content
View MugdhoAI's full-sized avatar
😄
Coding AI Projects & Building Skills
😄
Coding AI Projects & Building Skills

Highlights

  • Pro

Block or report MugdhoAI

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
MugdhoAI/README.md

All Asmaul Husnain · Mugdho

CS Student · Future AI Engineer · Builder
I build practical software, study computer science, and contribute to open source.

GitHub · LinkedIn · Email

Animated ASCII portrait Animated profile information card

AI and ML · C and C++ · Python · systems · developer tools · automation · open source

GitHub contribution snake animation

What I build

I enjoy taking an idea or a real problem and turning it into working software. My projects range from systems and databases to AI applications, developer tools, automation, and interactive software.

My current focus is:

  • AI and ML — Python, LangChain, Azure AI, AI agents
  • Systems and software — C, C++, data structures, databases, APIs
  • Developer tools — CLI applications, testing, validation, automation, CI/CD
  • Practical products — web applications, automation tools, and projects built around real problems
  • Cloud and deployment — Azure, Google Cloud, Netlify, and Vercel

Open source

I contribute to existing codebases by learning the surrounding implementation, solving concrete issues, adding tests, and responding to maintainer feedback.

Contribution What I worked on
Soup #1243 · merged Fixed Transformers 5 BatchEncoding handling in sequence distillation and added regression coverage
Soup #1053 · merged Fixed Rich markup handling for user controlled model names and added regression coverage
Provena #182 · merged Added regression coverage for top level CLI commands exposed in help output
pycubrid #378 · open Added strict positive integer validation for Cursor.arraysize across sync and async cursors
cubrid-mcp-server #1 · open Fixed SQL comment handling in audit categorization with regression coverage

My approach is simple: find a real problem, understand the existing code, make a focused change, test it, and verify the result.

Selected work

An interactive farming decision simulator built around one idea: test important decisions before real money is at stake.

A small SQLite style database engine built from scratch in C, covering SQL parsing, table operations, B tree storage, paging, persistence, testing, benchmarking, and sanitizers.

A lightweight search engine built from scratch in Python with tokenization, an inverted index, TF IDF ranking, Boolean queries, phrase search, JSON persistence, CLI support, tests, and CI.

A practical guide to setting up and working with AI coding agents, writing useful prompts, and getting reliable results.

A Python DB API 2.0 driver for CUBRID with synchronous and asynchronous interfaces, SSL/TLS support, and extensive testing.

An MCP server for working with CUBRID databases, focused on SQL safety, audit behavior, and reliable database tooling.

How I work

Understand → build → test → verify → document

I care about understanding why something works, not just getting it to run. I prefer simple architecture, useful tests, clear documentation, and projects that solve a real problem.

The contribution Snake is refreshed automatically from GitHub's public contribution data.

Pinned Loading

  1. Soup Soup Public

    Forked from MakazhanAlpamys/Soup

    Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

    Python 3

  2. sqlite-c sqlite-c Public

    A SQLite inspired relational database engine built from scratch in C.

    C 3

  3. search-engine search-engine Public

    A lightweight search engine built from scratch in Python, implementing document indexing, tokenization, inverted indexes, and relevance ranking without relying on external search engine libraries.

    Python

  4. MakazhanAlpamys/Soup MakazhanAlpamys/Soup Public

    Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

    Python 8.4k 1.3k