Skip to content

README.md

Latest commit

 

History

History
90 lines (61 loc) · 1.72 KB

README.md

File metadata and controls

90 lines (61 loc) · 1.72 KB

OER Agent

An AI-powered agent that helps students find open educational resources (OER) for their courses. It uses Claude to map a course name to search keywords, then queries ALG, OER Commons, and LibreTexts to return openly licensed materials.

Prerequisites

Install Node.js (if not installed)

Fedora/RHEL:

sudo dnf install nodejs -y

Ubuntu/Debian:

sudo apt install nodejs npm -y

Setup

1. Clone the repository

git clone https://github.com/KeysToRealities/Oer-Agent.git
cd Oer-Agent

2. Backend

cd backend

Create and activate a virtual environment:

python3 -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate

Install dependencies:

pip install -r requirements.txt

Copy the example env file and add your API key:

cp .env.example .env

Open .env and replace your_api_key_here with your actual Anthropic API key:

ANTHROPIC_API_KEY=your_api_key_here

Start the Flask server:

python app.py

The backend runs on http://localhost:5000.

3. Frontend

Open a second terminal:

cd frontend
npm install
npm run dev

The frontend runs on http://localhost:5173. Open that URL in your browser.

Usage

  1. Enter a course name or number (e.g. ENGL 1101, Introduction to Psychology)
  2. The agent maps it to search keywords using Claude
  3. Results are streamed in from Affordable Learning Georgia, OpenStax, Open Textbook Library, OER Commons, LibreTexts, and MERLOT
  4. Only openly licensed resources are returned
  5. Claude scores each resource and results are ranked by overall score