Documentation
ilearnassist is an AI study companion that runs on your own computer. It draws up a study plan, teaches it one item at a time, checks whether you actually understood with multiple-choice questions, and lays your questions and notes out in panels you can see. Everything lives in a folder you choose and is uploaded nowhere — except to the model provider you configure yourself.
Where to start
Section titled “Where to start”- Download and install — the installer (recommended) and the from-source route, plus which button to click when your OS objects to the unsigned build.
- First run — pick a data folder, create an admin, paste a key: six steps from installed to usable.
- Model providers — which ones are built in, how to configure them, and why the model list is empty.
- Guided Learning — how the built-in assistant runs a lesson.
- The seven widgets — Plan, Quiz, Threads, Notes, Figures, Insights and Resources.
Three things this project assumes
Section titled “Three things this project assumes”Your data stays yours. The app listens on 127.0.0.1 only. The one outbound connection is to
the model provider whose key you entered; web search and cloud document parsing happen only when you
ask for them. Uninstalling the app does not delete your data — it lives in the folder you chose on
first launch, separate from the program.
You pick the model provider. DeepSeek, Zhipu GLM, Qwen, Kimi, MiniMax, OpenAI and Google Gemini are built in, and any OpenAI-compatible service works too (Ollama, LM Studio, vLLM, your own gateway).
It is open source. MIT licensed, source on GitHub.