HackStack

Project Info

calvin

Devpost

Inspiration

the inspiration for this project actually came from my friend, calvin. he thought of this idea back back a long time ago (65 million years ago). my motivation for this project came from wanting to learn how to use the canvas apis and some of the sponsors' libraries / frameworks / services, so i thought that it would be an interesting project to do while drinking pocari sweat and eating the free food.

What it does

to preface, canvas is a learning management system (lms) that is used by many schools including stanford, and you can imagine this application as an add-on to the lms. calvin is your personal chatbot when it comes to canvas courses and assignments. select a school subject then click on an assignment. you can, then, ask calvin about your assignment. also, you can even ask the chatbot about all your classes. you don't have to specify which assignment. you can even whiteboard out your query if you feel like it.

How we built it

frontend next.js - the core of our frontend shadcn/ui - the component library backend fastapi - the core of our backend chromadb - the vector database groq - used their hosted llm models canvas api - the api we used to fetch the assignments / coursework langgraph - to create cool ai agents dev tools windsurf ide - sped up development time by a century system design

Challenges we ran into

i went solo experimented with many vector databases before deciding to use chromadb slept early and wanted to relax during this hackathon i wanted to have fun got distracted by llamas

Accomplishments we're proud of

my first solo hackathon made it easier for students to ask questions about their canvas assignments implemented the whiteboard feature so students can draw out their questions more and more and more rag

What we learned

learned how to use chromadb's cloud service learned how to use groq's llama vision models learned to have lots of fun

What's next

implement tool calling integrate ai agents that can do deep research or problem solving

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • FastAPIIn code
  • Next.jsIn code
  • PythonIn code
  • ReactIn code
  • Tailwind CSSIn code
  • TypeScriptIn code
  • LangChainClaimed

7 of 8 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

58 KB

Source files

26

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars