Structure

Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.

Languages

Share of indexed source by file size. Binary and vendored files are excluded.

Dependencies

Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.

Feature verification

• Fetch.ai uAgents framework used to build agent systemVerified

  We used the Fetch.AI framework...to create a multi-agent study tool generation system

  Claimed on Devposthigh confidence

  • agents/bureau.py:1 — Imports and uses uagents.Bureau to combine multiple Agent instances
  • agents/contentChecker.py:2 — Uses uagents Agent, Context, Model, and fund_agent_if_low from the Fetch.ai uagents SDK
• Firebase user authenticationVerified

  User authentication was handled with Firebase

  Claimed on Devposthigh confidence

  • react-front/src/contexts/AuthContext.js:19 — signUp/logIn/logOut wrap Firebase's createUserWithEmailAndPassword, signInWithEmailAndPassword, and signOut
  • react-front/src/config/firebase.js:15 — Firebase app initialized and getAuth exported for use in AuthContext
• Groq LLM integrationVerified

  along with the Groq library LLM integration

  Claimed on Devposthigh confidence

  • agents/contentCleaner.py:25 — Instantiates a Groq client with GROQ_API_KEY and calls chat.completions.create with model llama3-8b-8192
  • agents/quiz_generator.py:40 — Groq client used to combine quiz JSONs via chat completion
• Project name/repo (calhacksofficehours)Verified

  calhacksofficehours

  Claimed on readmehigh confidence

  • README.md:1 — README title matches the repo/project name claim
• Python backend handling agent communication via POST requestsVerified

  a python backend handling agent communication through post requests and context handling

  Claimed on Devposthigh confidence

  • agents/contentCleaner.py:82 — on_rest_post('/rest/post', ...) handler receives a POST request with a filename and kicks off the agent pipeline via ctx.send
  • react-front/src/pages/ExamPage.jsx:79 — Frontend POSTs to /rest/post with a filename to trigger note processing
• React front endVerified

  Our front end was built using React

  Claimed on Devposthigh confidence

  • react-front/src/App.js:1 — React app entry with routed pages (Home, Note, Login, SignUp, Landing)
  • react-front/package.json — Lists react-router-dom and other React dependencies
• TinyMCE rich text editor for notesVerified

  our rich text editor incorporated TinyMCE

  Claimed on Devposthigh confidence

  • react-front/src/pages/NotePage.jsx:18 — Imports @tinymce/tinymce-react Editor and renders it with an apiKey and plugin/toolbar config for note editing
  • react-front/package.json — @tinymce/tinymce-react is a listed dependency
• LLM content validation to reduce hallucinationsCode-supported

  We then implemented LLM content validation to ensure materials are logical and accurate...agents to ensure content is validated at each step

  Claimed on Devpostmedium confidence

  • agents/contentChecker.py:34 — summary_check_prompt asks an LLM to verify a summary against original notes for missing/incorrect info, and content_cleaner incorporates this feedback into a revised summary
  • agents/quizCheck.py:44 — A separate quiz-checking agent exists but its on_message handler is entirely commented out, so this validation path is not actually active
• Multi-agent system for summarization, flashcard, and Q&A generationCode-supported

  Used a multi-agent AI system to handle summarization, flash card and Q&A generation

  Claimed on Devpostmedium confidence

  • agents/bureau.py:8 — Bureau registers true_or_false, quiz_generator, short_answer, content_checker, content_cleaner agents together
  • agents/contentCleaner.py:82 — content_cleaner summarizes notes then sends to short_answer and true_or_false agents, which generate quiz questions
  • agents/quizAgent.py:22 — A separate quizAgent duplicates the short_answer agent's name/port/seed (both 'quizAgent'/'quizphrase'/8002), suggesting incomplete/inconsistent wiring across agents
• Note-taking and study tool generator (overall product)Code-supported

  An all-in-one note-taking and study tool generator

  Claimed on Devpostmedium confidence

  • react-front/src/pages/NotePage.jsx:1 — NotePage combines a note editor (TinyMCE, Firestore persistence) with an exam/study tool generator triggered from FuncBar
• Study tool generation from user notes (practice exams, flashcards, quizzes)Code-supported

  Generates study tools such as practice exams, flashcards, or short form quizzes using your own notes

  Claimed on Devpostmedium confidence

  • react-front/src/pages/ExamPage.jsx:62 — Fetches generated quiz JSON from backend and renders it via TestWindow (practice test) and Flashcard components
  • agents/quiz_generator.py:44 — Combines short-answer and true/false quiz JSON into a final quiz written to quiz_data.json
  • react-front/src/pages/ExamPage.jsx:186 — The 'Summary' view is hardcoded static HTML for two specific note titles (Genetics/Physics), not actually generated from user notes, showing the pipeline is not fully wired end-to-end
• Mobile app for study toolsClaimed only

  We wanted to build a web and mobile app for study tools generated from our own notes

  Claimed on Devposthigh confidence

An AI agent derived these features from the project’s Devpost page and readme, then searched the code for each one. Verified features are backed by cited code; claimed-only features had no supporting code, which is not by itself proof a feature is missing.