md2anki is a free and open-source web app that uses AI to generate Anki flashcards from Markdown files you upload.
This AI-powered flashcard generator is built upon Vercel AI SDK, GPT-4o-mini, Next.js, Langfuse, and Seline.so under the hood.
By deploying it locally, on your own server, or using the official web app, you can quickly transform your notes, documents, and other text-based content into study materials.
I tested md2anki’s capabilities by uploading the ReadMe file of the popular JavaScript library GrapesJS. The AI successfully generated 40+ flashcards covering key concepts, installation instructions, plugin functionalities, and more.
For example, it generated cards asking “What is GrapesJS?”, “What is the main purpose of GrapesJS?”, and even fill-in-the-blank questions like “Fill in the blank: GrapesJS is designed to be used inside a _ to speed up the creation of dynamic templates.”
What makes this particularly useful is the ability to review and customize these cards. You can edit the questions and answers to match your learning style and the information you find most relevant.
Once satisfied, you can download the flashcards as an .apkg file, a format designed for Anki, the popular flashcard-based studying program.
How to use it:
1. Go to the md2anki website and upload a Markdown file (.md) that contains the information you want to turn into flashcards. This could be anything from lecture notes to detailed articles.
2. Click the “Generate flashcards” button, and the AI-powered engine will transform your Markdown into flashcard decks.
3. You can then edit the question, answer, or both on each card. This allows you to correct any inaccuracies, add context, or rephrase for clarity.
4. Download the flashcards as a .apkg file and import it into the Anki app. You now have a new deck of flashcards ready to aid your study sessions.
How to deploy it:
For those interested in deploying md2anki on their local environment, follow these steps to set up the application using your own API.
1. Make sure you first have the following dependencies installed:
- Node.js (v14 or later)
- npm or yarn
- OpenAI API key
- (Optional) Seline.so and Langfuse accounts for analytics
2. Clone the md2anki repository from GitHub.
git clone https://github.com/yourusername/md2anki.git
3. Navigate to the project directory and install the necessary packages using npm or yarn:
cd md2anki
npm/yarn install
4. Create a .env.local file in the root directory of your project. Add your API keys and other optional variables:
OPENAI_API_KEY=your_openai_api_key
OPENAI_MODEL=your_openai_model (optional, defaults to `gpt-4o-mini-2024-07-18`)
LANGFUSE_PUBLIC_KEY=your_langfuse_public_key (optional)
LANGFUSE_SECRET_KEY=your_langfuse_secret_key (optional)
LANGFUSE_HOST=your_langfuse_host (optional)
5. Launch the development server to start running md2anki locally:
npm/yarn run dev
6. Open a web browser and navigate to http://localhost:3000 to view and start using the md2anki application.
