h9-tec

h9-tec / graduation-project-advisor

Public

Arabic-first LLM-backed advisor that helps Egyptian CS students pick a production-grade graduation project — onboarding form → 5 ranked idea cards → supervisor-ready blueprint. Next.js 15, FastAPI, Qdrant, Azure OpenAI + Ollama.

22
2
100% credibility
Found Apr 19, 2026 at 22 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A bilingual web tool that generates personalized, research-grounded graduation project ideas and detailed blueprints for computer science students.

How It Works

1
🌐 Discover the advisor

You land on a welcoming page that promises real project ideas grounded in fresh research and code.

2
📝 Share your story

You fill a simple form about your skills, time available, team, favorite tools, and what excites or turns you off.

3
💡 See your ideas light up

Five unique project cards appear instantly, each tied to a real paper or repo, ranked just for you.

4
Tweak or dive in
✏️
Refine ideas

Add a note like 'more AI agents, less web stuff' to get fresh suggestions.

📋
Expand a card

Click any idea to unlock a detailed blueprint with steps, risks, and resources.

5
❤️ Save your favorites

Heart the best ones to build a shortlist and compare side-by-side.

🎓 Project plan ready

Walk away with a supervisor-approved blueprint, complete with milestones and real references to impress everyone.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 22 to 22 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is graduation-project-advisor?

This Arabic-first, LLM-backed advisor helps Egyptian CS students pick production-grade graduation projects. Users fill a quick onboarding form with domains, skills, timeline, team size, preferred stacks, interests, and avoids—then get five ranked idea cards grounded in real arXiv papers and GitHub repos. Tap a card for a supervisor-ready blueprint with 13 sections like milestones, datasets, risks, and eval metrics. Built on Next.js frontend, FastAPI backend, Qdrant vector store, and Azure OpenAI or Ollama.

Why is it gaining traction?

Unlike generic chatbots or paper searches, it delivers verifiable, tailored ideas with no hallucinations—every card cites live sources, and blueprints inject real URLs post-generation. Arabic RTL support, free-text refinements with undo, and anonymous sessions make it frictionless. Live ingestion from HF papers, arXiv, and GitHub trending keeps ideas fresh.

Who should use this?

Egyptian undergrads tackling capstone theses who need research-grounded shortlists without prompt engineering. Academic advisors short on time for curation. Early PhD students or engineering managers scouting R&D directions with milestone plans.

Verdict

Solid niche tool with excellent Docker Compose setup and API docs—spin it up in minutes for local Ollama runs. At 22 stars and 1.0% credibility, it's early but mature enough to fork; private license TBD limits adoption.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.