Learn (Almost) Anything
Type a topic. Get a real course — with lessons, diagrams, tests, homework and spaced review — built by the AI subscription you already pay for, stored on your own machine.
Desktop app for macOS and Windows · free · open source
Everyone "learns with ChatGPT" now — and a week later all that is left is a chat transcript you will never reopen. Chats answer questions; they do not teach. Real learning needs structure, practice, feedback and repetition. That bugged me, so I built a tool that turns "I want to understand X" into an actual course.
An agent interviews you, researches the topic, designs a curriculum, writes illustrated lessons, quizzes you, grades your homework, and schedules flashcard reviews so the material sticks. There is no platform of ours, no server with your data — the engine is the Claude Code or Codex CLI you already have. It is the difference between asking a smart friend questions all evening and having that friend sit down and teach you properly.
Topic, language, format — and go
You pick a topic, language, format and agent. The course can be a full academic course, a compact mini-module, a podcast-style series, a single lesson — or a roadmap that maps the whole journey first. Do not want the full treatment? Checkboxes at creation turn tests and homework off, and you can skip the clarifying interview entirely: title, plan, go.
The full learning loop
Most AI tools stop at "here is some text". This one closes the loop:
- Lessons that look like lessons — articles with real sourced images, Mermaid diagrams, galleries and sandboxed interactive widgets. Every draft goes through an editor and fact-check pass before you see it.
- Comprehension tests — question pools that check understanding, not verbatim recall, and interleave concepts from earlier modules.
- Real homework — essays, diagrams, file uploads, GitHub repos, and autograded coding tasks that actually run your code. The agent reviews submissions and makes you retry until it passes.
- Spaced repetition — flashcards are extracted from each lesson and scheduled for review, so the course keeps working on you after you have read it.
- Lecture audio — free OS voices out of the box, optional premium Gemini TTS, cached on disk.
Roadmaps: see the whole journey
For big goals ("become a data engineer", "learn academic painting from zero") a single course is the wrong shape. A roadmap lays out stages and skills, runs a quick diagnostic to find out what you already know, and spawns a lesson or a full course from any skill — each one aware of where it sits in the bigger picture.
Your materials, your sources
Drop documents, links and folders into a Space and courses created there ground themselves in your material — strictly (only your sources) or openly (your sources first, the web second). Attach custom MCP servers to a course and the agent can research through any tool you trust.
Catalog: public and private
Publish your best courses to the public catalog, install other people's courses, and translate any course into another language — structure, lessons, tests, homework, diagram labels and even baked-in image text included. For teams, spin up your own catalog inside your infrastructure with one Docker command, hidden from the public internet: a shared internal course library for onboarding, domain knowledge and tooling guides. Authors publish with the team token; everyone else just browses and installs.
Your subscription is the engine
The app is free and runs no paid backend. Every LLM call goes through an agent CLI already installed and authenticated on your machine: Claude Pro/Max → Claude Code CLI, ChatGPT/Codex plan → Codex CLI. Install both and pick per course. Optional extras, each off by default: Brave Search API (web and image grounding), Gemini API (generated illustrations, premium TTS). A quality/cost tier per course (quick / balanced / premium) controls research depth and how much material gets generated — so a quick mini-course stays cheap and a premium deep-dive goes all in.
Get started
- Download the latest build from Releases — macOS
.dmg(Apple Silicon / Intel, signed and notarized) or Windows.msi/.exe. - Make sure Node.js 20+ is installed — the local sidecar runs the agent SDKs through it.
- Have at least one agent CLI (Claude Code or Codex) logged in, then launch the app and create your first course.
The UI ships in English and Russian; course content can be generated in any language — a single library happily mixes English, Russian and Chinese courses. Installed builds self-update through GitHub Releases.
Under the hood
Tauri 2 (desktop shell) · React 19 + TypeScript + Vite · Node sidecar calling @anthropic-ai/claude-agent-sdk and @openai/codex-sdk · SQLite + files for local storage · Playwright + system Chrome for visual widget checks · bundled MCP servers for controlled research tools.
Links
Learn (Almost) Anything is a free, open-source desktop app for macOS and Windows that turns any topic into a complete course. Type what you want to learn and an AI agent interviews you, researches the topic, designs a curriculum, writes illustrated lessons, builds tests, grades homework, and schedules flashcards for spaced repetition.
The core idea is that the engine is an agent CLI (Claude Code or Codex) already installed and paid for on your own subscription. The app runs no paid backend and sends nothing to a third-party server: courses, progress and media live locally in SQLite and files. It supports roadmaps for big goals, Spaces for grounding on your own materials, autograded coding assignments and lecture audio.
Courses can be published to the public catalog at catalog.almost-anything.io, installed from other authors and translated into other languages in full. Teams can run a self-hosted private catalog in Docker inside their own infrastructure. Stack: Tauri 2, React 19, TypeScript, a Node sidecar using the Claude Agent SDK and Codex SDK, and SQLite. The source is open.