Marvin
Web app to automatically generate subjective or an objective test and evaluate user responses without any human intervention in an efficient and automatic manner using machine learning and natural language processing.
Install / Use
/learn @nityansuman/MarvinREADME
MARVIN - AI Examination System
Conducting examination and answer sheet evaluation are hectic testing tools for assessing academic achievement, integration of ideas and ability to recall, but are expensive, resource and time consuming to generate question and evaluate response manually. Manual evaluating of answer sheet takes up a significant amount of instructors' valuable time and hence is an expensive process. Also different security concerns regarding paper leakage is one of the other challenges to conquer. This project aims to build an automated examination system using machine learning, natural language toolkit (NLTK), python environment, flask framework, and web technologies to provide an inexpensive alternative to the current examination system. We implement a model to automatically generate questions with their respective answers and assess user responses.

Getting Started
Download or clone the project from github:
$ git clone https://github.com/nityansuman/marvin.git
Create a project environment (Anaconda recommended):
$ conda create --name envname python
$ conda activate envname
Install NLTK prerequisites:
$ python
>>> import nltk
>>> nltk.download("all")
>>> exit() # after download is complete, exit python
Run project:
$ cd marvin
$ python runserver.py
Login Board

Result Board

Support
If you like the work I do, show your appreciation by 'FORK', 'STAR' and 'SHARE'.
Related Skills
claude-opus-4-5-migration
85.3kMigrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5
model-usage
342.5kUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
TrendRadar
50.2k⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。
mcp-for-beginners
15.7kThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.
