RecallFlow AI

Generate AI-powered flashcards from your Obsidian notes, then review them using the FSRS (Free Spaced Repetition Scheduler) algorithm — all locally within your vault.

---

✨ Features

🧠 AI Flashcard Generation

• From selection — highlight text and generate a single focused card via right-click or command palette
• From entire note — process the full Markdown document into 3–6 mixed-type flashcards
• Preview & refine — inspect, edit, and regenerate AI-generated cards before saving
• Three card types: Q&A, Cloze (fill-in-the-blank), Multiple Choice

📆 FSRS Spaced Repetition

• Cards follow FSRS across 4 lifecycle states: New → Learning (~10min–1d) → Review (e.g., 3d ➔ 10d ➔ 1mo) → Relearning (≤1d)
• Interactive review: typed answers for Q&A, fill-the-blank for cloze, tap-to-select for choice
• Four ratings: Again (1), Hard (2), Good (3), Easy (4) to fine-tune memory curve
• Configure maximum new and review cards per day

🔥 Cramming Mode (Rerun)

• Re-quiz today's reviewed cards without affecting FSRS scheduling
• Full state persistence — navigate freely without losing answers

📋 Card Manager

• Search, edit, validate, and delete flashcards
• View metadata: card type, FSRS state, last review, due date, source, creation time

📊 Activity Heatmap

• 12-month GitHub-style contribution grid of daily review counts

🌐 Multi-Language UI

• English, 中文, 日本語, 한국어
• AI-generated card language configurable independently

🔒 Privacy-First

• No telemetry, no background network requests
• All data stored locally in vault plugin data
• Review works entirely offline

---

📖 How It Works

1. Configure your LLM endpoint (base URL, API key, model) in Settings → RecallFlow AI
2. Generate cards from selection or entire note via commands, ribbon, or right-click
3. Preview in the generation modal — edit, regenerate, then confirm to save
4. Review due cards in the immersive modal — answer, rate, repeat
5. Rerun to cram today's cards without resetting the FSRS algorithm
6. Manage your card library with search, edit, and validation tools

---

🚀 Installation

Method	Steps
Community Plugins	Settings → Community plugins → Browse → "RecallFlow AI" → Install & Enable
BRAT	Add repo URL in BRAT → Enable plugin
Manual	Download main.js, manifest.json, styles.css → copy to <vault>/.obsidian/plugins/recallflow-ai/ → Reload & Enable

---

⚙️ Settings

Setting	Description
Base URL	OpenAI-compatible endpoint (default: https://api.openai.com/v1)
API Key	Credential — stored locally in vault data
Model	Model ID (e.g., gpt-4o, claude-3-5-sonnet, deepseek-chat)
Test Connection	Verify your API key, base URL, and model configuration
UI & Card Language	Interface language + default AI card language
Max New / Day	Cap on new cards per day across all sessions
Max Review / Day	Cap on due review cards per day across all sessions
Rerun Today's Cards	Cramming mode — re-quiz without FSRS impact
Edit Cards	Open Card Manager to browse/search/edit/delete
Activity Heatmap	12-month daily review visualisation

---

🎯 Commands

Command	Description
Start review session	Open review modal for cards due today
Generate AI flashcards from selection	Create cards from highlighted text
Generate AI flashcards from entire note	Create cards from active Markdown note

Right-click context menu also offers generation when text is selected.

---

💬 Card Types

Type	Front	Answer
Q&A	Open-ended question	Free-text answer
Cloze	Sentence with {____} blanks	Array of terms
Choice	Question + 4 options (A–D)	One correct option

All three types are generated together. The AI decides the mix based on your note content.

---

🔧 Development

Requirements: Node.js 18+, npm

npm install
npm run dev       # Watch mode — writes main.js on change
npm run build     # Production bundle
npm run lint      # ESLint check

Copy main.js, manifest.json, styles.css into <vault>/.obsidian/plugins/recallflow-ai/ for local testing.

Project Structure

src/
├── main.ts                    Entry point, commands, ribbon, menus
├── types.ts                   Type definitions, defaults
├── services/
│   ├── fsrsService.ts         FSRS-5 scheduler, due-card queue, limits
│   ├── i18n.ts                Translations (en / zh / ja / ko)
│   └── llmService.ts          LLM prompt, API call, parser
└── ui/
    ├── cardManageModal.ts     Browser, search, edit, delete
    ├── cardPreviewModal.ts    AI preview with editing & regenerate
    ├── reviewModal.ts         Interactive review, ratings, cramming
    └── settingsTab.ts         Settings, test connection, heatmap

Tech Stack

Dependency	Role
Obsidian API	Plugin lifecycle, UI, vault I/O
TypeScript	Type-safe development
esbuild	Bundling to main.js
ESLint + eslint-plugin-obsidianmd	Code quality

---

🔒 Privacy & Data

• No telemetry — zero background network requests
• Generation data: note text + model name → your configured LLM endpoint only
• All data local — cards, history, stats, settings stored in vault plugin data by Obsidian

---

📄 License

0BSD

🤝 Contributing

See CONTRIBUTING.md. Open an issue for large changes, submit PRs that pass npm run build && npm run lint.

📚 Releasing

See RELEASING.md for the release checklist and Community directory submission process.