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 a personal learning assistant that uses a three-layer memory system and a proactive scheduler to provide personalized, evidence-driven educational support.

  • 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

    pi‑subagents is a Pi AI‑assistant extension that lets the main Pi session spawn focused child agents (scout, reviewer, worker, oracle, etc.) to handle tasks like code review, research, implementation, and auditing. Subagents can run in the foreground (streaming live) or in the background (detached process). Users simply install the package (`pi install npm:pi-subagents`) and then ask Pi in plain language (e.g., “Use reviewer to review this diff”). The system orchestrates the child agents, provides observability via a FleetView panel, and offers configuration options such as tool activation and spawn limits.

  • Project
    ai-shifu/ai-shifu

    AI‑Shifu is an open‑source, Docker‑based platform that converts a single lesson framework into a personalized AI tutor. It uses LLMs to generate custom explanations, interactive Q&A, and assessments, and can be embedded in websites or corporate training portals.

  • Project
    nicobailon/pi-intercom

    Pi‑intercom is a Pi‑extension that adds a local broker and a `/intercom` UI/tool, letting multiple Pi AI‑agent sessions on the same machine send, ask, reply, hand‑off, and cancel messages one‑to‑one. It supports aliases, blocking asks, safety knobs, and integrates with pi‑subagents for supervisor escalation, enabling coordinated multi‑agent workflows like planner‑worker delegation.