amosblomqvist/learn

My AI learning system.

What it solves

It provides a structured AI-driven learning system designed to help users acquire new knowledge through a specific teaching philosophy, interactive quizzes, and visual aids.

How it works

The system is built as a configuration for the pi framework. It uses a "teaching skill" to guide the learning process and delegates specialized tasks to subagents: a researcher for truth verification and visual makers (SVG and Mermaid) for creating diagrams. It also includes extensions for graded quizzes with instant feedback and a UI popup system for asking the user questions.

Who it’s for

Learners who use the pi framework and want a personalized, agentic approach to studying new topics.

Highlights

  • Interactive quizzes with instant feedback and explanations.
  • Automated diagram generation via specialized SVG and Mermaid subagents.
  • A research subagent for verifying information.
  • Integration with markdown logs to track learning sessions.

Related

  • Project
    hhyqhh/inno-agent

    Inno Agent is an open‑source personal learning AI built on the Pi coding‑agent SDK. It adds three memory layers (learner profile, wiki, session logs), a natural‑language scheduler, IM channel support (Feishu/WeChat), and an in‑browser practice lab. Available as an Electron desktop app, a React web UI, or a terminal CLI, it works with any OpenAI‑ or Anthropic‑compatible model and can be extended via a skill hub. The project is MIT‑licensed and includes Docker, sandboxing, and a session‑replay showcase.

  • Project
    cheshire-cat-ai/core

    An AI agent framework designed for education and research, allowing users to easily build, understand, and extend AI agents and publish them on the web.

  • Project
    nicobailon/pi-subagents

    A delegation framework for Pi that allows a parent session to spawn focused child agents for specialized tasks like code review, research, and implementation.

  • Project
    ai-shifu/ai-shifu

    An AI-powered teaching agent that transforms expert knowledge and course frameworks into personalized, one-on-one learning experiences for students.

  • Project
    nicobailon/pi-intercom

    A communication extension for Pi agent sessions that enables direct 1:1 messaging and coordination between multiple AI agents running on the same machine.