Project Info
Inspiration
In 2022, 1.2 million students in the US took AP exams. While the usage of one-on-one tutoring has soared in high-income communities since 1997, other students are left behind and have to make do with juggling several website and textbooks. During high school, we also took several AP exams and had to alternate studying from several different resources such as our textbooks, practice exams, online audio practice and many more. Our tool consolidates all of these into 1 singular website to help the AP student focus on studying for the exam.
What it does
Our core features include an AI tutor chatbot Custom unit quizzes Custom remedial quizzes on topics you struggled with Expert full-length practice exams Progress tracker on each unit and topic For language courses, listening and speaking practice as well as spoken conversation with AI
How we built it
We created Letta AI agents that were trained on AP course Course and Exam Description PDFs as well as practice free-response questions and their scoring guidelines. Then, we integrated VAPI so that students taking AP Spanish and French can practice conversation with the AI and learn how to answer questions for the AP exam. Finally, we used Vercel to build and deploy our user interface which is clean and readable in light and dark mode.
Challenges we ran into
Of the many challenges we ran into, one of the most prominent challenges we faced was trying to integrate the AI agent with the front-end. Since this was our first time using them, there was a steep learning curve. Similarly, integrating VAPI into the final product was difficult for the same reasons. Additionally, v0 which built the frontend, hard-coded alot of the quizzes and practice exams, so we needed to rewrite many of the files so that the final product could work.
Accomplishments we're proud of
Successfully using AI agents Integrating Voice-Powered AI Agents for Spanish and French Deploying the final product on Vercel Creating a product that would have helped us a lot back in high school and that we hope can help many more AP students in the future
What we learned
how to use AI agents with Letta and Voice-Powered AI agents with VAPI how to debug a large project how to manage a multimodal multi-agent framework
What's next
adding more AP courses making an enterprise option for small to large-scale businesses for onboarding making a teacher login so that they can upload their notes, so their students can practice
AP Tutor - AI-Powered Learning Platform
A comprehensive AI tutoring platform for AP courses using Letta's stateful agents. Each course has a dedicated AI tutor that remembers student interactions and adapts to individual learning needs.
Features
- 6 AP Courses: Biology, US History, Spanish, French, Chemistry, Computer Science A
- Personalized AI Tutors: Each course has a specialized Letta agent with deep curriculum knowledge
- Adaptive Learning: Agents remember student strengths/weaknesses and provide targeted help
- Interactive Practice: Unit quizzes, review sessions, and full-length practice exams
- Language Learning: Speaking/listening practice for Spanish and French courses
- Progress Tracking: Detailed analytics and progress visualization
Quick Start
-
Clone and Install ```bash git clone cd ap-tutor-platform npm install ```
-
Get Letta API Key
- Sign up at app.letta.com
- Create an API key at app.letta.com/api-keys
-
Setup Environment ```bash cp .env.example .env.local
Add your LETTA_API_KEY to .env.local
```
-
Create AI Tutors ```bash npm run setup-agents ```
-
Start Development Server ```bash npm run dev ```
Architecture
The platform uses Letta's stateful agents [^1] to create persistent AI tutors that:
- Remember Everything: Each agent maintains memory of student interactions
- Adapt Over Time: Agents learn student strengths/weaknesses and adjust teaching
- Provide Expertise: Each tutor has comprehensive AP curriculum knowledge
- Track Progress: Agents store learning patterns in their long-term memory
Agent Memory Structure
Each tutor agent has specialized memory blocks:
- Persona: Teaching style and expertise
- Course Knowledge: Complete AP curriculum and exam format
- Student Progress: Individual learning patterns and weak areas
- Human: Student profile and preferences
Course Coverage
AP Biology
- 8 units from Chemistry of Life to Ecology
- Lab analysis and data interpretation
- FRQ practice and exam strategies
AP US History
- 9 historical periods from 1491-Present
- DBQ and LEQ writing practice
- Primary source analysis
AP Spanish/French
- 6 thematic units with cultural focus
- Speaking and listening practice as well as AI conversation
- Authentic resource integration
AP Chemistry
- 9 units covering all major chemistry concepts
- Mathematical problem-solving
- Laboratory skills and analysis
AP Computer Science A
- 10 units of Java programming
- Object-oriented programming concepts
- Algorithm development and analysis
Technology Stack
- Frontend: Next.js 14, React, TypeScript, Tailwind CSS
- AI Agents: Letta Cloud with GPT-4.1 models
- UI Components: shadcn/ui with Radix primitives
- Styling: Tailwind CSS with custom design system
Development
Adding New Features
The platform is designed for easy extension:
- New Courses: Add course configs to
scripts/setup-agents.js - Enhanced Quizzes: Extend
QuizSectioncomponent with new question types - Progress Analytics: Add new metrics to
ProgressDashboard - Language Features: Expand
LanguageSectionwith more interactive elements
API Integration
The chat interface uses the Vercel AI SDK with Letta provider [^1]:
```typescript import { lettaCloud } from '@letta-ai/vercel-ai-sdk-provider' import { streamText } from 'ai'
const result = streamText({ model: lettaCloud(agentId), prompt: userMessage, // Only send new message, not history }) ```
Deployment
- Environment Variables: Ensure all
LETTA_AGENT_*variables are set - Build:
npm run build - Deploy: Compatible with Vercel, Netlify, or any Node.js hosting
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Test with your Letta agents
- Submit a pull request
License
MIT License - see LICENSE file for details.
Analysis
View
Metric
- 13
- 1
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
- CSSIn code
- JavaScriptIn code
- Next.jsIn code
- ReactIn code
- Tailwind CSSIn code
- TypeScriptIn code
- Google GeminiClaimed
- Node.jsClaimed
- VercelClaimed
6 of 9 appear in the indexed code. 3 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
544 KB
Source files
83
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
usrnme20/IntelliAgent
95 files · 557 KB · @ 2a72123
Structure
Interface
66 files · 69%Screens, components and styles rendered to the user.
API & routing
10 files · 11%Request entry points: routes, handlers and controllers.
Application logic
4 files · 4%Domain rules, services and shared utilities.
Supporting
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
- TypeScript57%
- YAML39%
- JavaScript2%
- Markdown1%
- CSS1%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
package.json
npm · 60- @letta-ai/letta-client
- @radix-ui/react-accordion
- @radix-ui/react-alert-dialog
- @radix-ui/react-aspect-ratio
- @radix-ui/react-avatar
- @radix-ui/react-checkbox
- @radix-ui/react-collapsible
- @radix-ui/react-context-menu
- @radix-ui/react-dialog
- @radix-ui/react-dropdown-menu
- @radix-ui/react-hover-card
- @radix-ui/react-label
- @radix-ui/react-menubar
- @radix-ui/react-navigation-menu
- @radix-ui/react-popover
- @radix-ui/react-progress
- @radix-ui/react-radio-group
- @radix-ui/react-scroll-area
- +42 more
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.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.