ScholarAI
Open-source AI study app that turns lectures, documents, and videos into…
AI: local or online
not yet reviewed by publik. It is live now; the founder has not reviewed this version yet.
by 
Where ScholarAI’s AI runs, and what it costs
Prices are for one typical use: one request of about 1,500 words sent and 375 words back. A higher quality score is better.
On your computer
- Price
- Free per use. Your computer does the work.
- Runs with
- llama.cpp
- Memory
- Llama 3.1 8B is a 4.9 GB download at 4-bit. gpt-oss 20B runs on systems with as little as 16GB memory. Faster with Apple silicon or a graphics card.
- Quality
- Llama 3.1 8B: 7
publik API
- Price
- $0.0100 per use, $10.00 per 1,000 usespublik-balanced, the default level
- Quality
- MiMo-V2.6-Pro: 46
- Setup
- Not built into ScholarAI yet. A publik API key works wherever ScholarAI takes an OpenAI-compatible address.
Your own key
- Price
- $0.0013 per use, $1.31 per 1,000 usesMiMo-V2.6-Pro at OpenRouter’s list price, before its fee for buying usage
- Quality
- MiMo-V2.6-Pro: 46
- Setup
- Open a provider account, add a card, paste the key into ScholarAI.
Quality and price, side by side
| Model | Quality | Per 1,000 uses |
|---|---|---|
| On your computer (Ollama, 4-bit download size) | ||
| Granite 4.2 3B2.2 GB | 9 | $0 |
| Phi-4 Mini2.5 GB | 6 | $0 |
| Llama 3.1 8B4.9 GB | 7 | $0 |
| gpt-oss 20B14 GB | 9 | $0 |
| Gemma 4 31B20 GB | 19* | $0 |
| Qwen3.5 35B-A3B24 GB | 19* | $0 |
| publik API | ||
| publik-fastGLM-5.3 Flash | 42 | $1.00 |
| publik-balancedMiMo-V2.6-Pro · ScholarAI | 46 | $10.00 |
| publik-smartGPT-6 Sol | 48 | $18.00 |
Quality: Artificial Analysis Intelligence Index v4.3.2, read 2026-09-22 (publik API models 2026-09-25); * = estimated by Artificial Analysis. Sizes: the Ollama library, read 2026-09-22.
What you pay for
- On your computer: nothing per use. You pay in disk space, memory and electricity, at lower quality.
- publik API: publik’s published price for each use, in dollars, from your publik balance. It is above the model’s cost; the difference runs publik and pays the app’s builder.
- Your own key: the provider’s price, billed to an account you keep with the provider.
How to install ScholarAI
Every step written out. No terminal experience needed. Pick your setup.
README
Open in GitHubScholarAI
Turn what you're studying into lessons, notes, flashcards, quizzes, and study sessions.
ScholarAI is an open-source desktop study application for macOS and Windows. It turns your own material into a calm, source-grounded learning workflow, with optional AI that runs privately on your computer.
Features
- Generated Lessons — ordered 3–10 minute lessons with explanations, examples, checkpoints, progress, and source excerpts.
- Notes — editable, saved notes with Markdown export.
- Flashcards — generated cards with Again, Hard, Good, and Easy spaced review.
- Quizzes — standalone question flows with explanations and stored attempts.
- Ask — class-level chat grounded in imported source chunks.
- Study Mode — unfinished lessons, weak concepts, due cards, and practice from real performance.
- Personalization — branching first-launch onboarding and preferences used in lesson generation.
- Privacy — user files, history, credentials, and downloaded models remain outside the source tree.
- Appearance — monochrome Light, Dark, and System modes.
https://github.com/user-attachments/assets/2bc8195b-4c70-4e5d-90f0-e8cc33a044ea
Local AI setup
During onboarding, choose Built-in Local AI or another OpenAI-compatible provider. This choice never starts a download. When you are ready, open Settings → Models to explicitly download Qwen 2.5 3B (the default local model, about 2.1 GB) or Qwen3 1.7B (lightweight, about 1.3 GB). ScholarAI checks disk space, shows real byte progress, supports cancellation and resume, verifies SHA-256, starts packaged llama.cpp, and tests the model before showing Ready. Models are not included in the installer.
Building from source
Node.js is required only for contributors—not for people using an installer.
npm install
npm run typecheck
npm run lint
npm test
npm run dev
npm run dev starts the Electron desktop app. Packaging commands download the pinned llama.cpp runtime for the requested target:
npm run package:mac
npm run package:mac:x64
npm run package:win
Privacy
Imported documents and generated study data are stored locally. Model files and provider configuration live in Electron's operating-system application-data directory. Custom provider API keys use Electron safeStorage where available. .gitignore excludes model/runtime artifacts, environment files, exports, and local data directories.
Contributing
See CONTRIBUTING.md, SECURITY.md, and CODE_OF_CONDUCT.md. Attribution is in THIRD_PARTY_NOTICES.md.
License
ScholarAI is available under the MIT License. Downloaded Qwen models retain their model-specific upstream licenses; llama.cpp is MIT licensed.