algotutor — AI-powered training for Go developers

3 min read Original article ↗

A personal tutor for accelerated learning. For Go developers.

Sub-problems when you're stuck. Review cards from every mistake. Re-solves spread out over months. A concept ladder that progresses with your level.

algotutor — algos

$ make train

Concept: hash-maps — level 1 → 2

Problem: two-sum-variant

Generated 47 lines. Solve in main.go,
then say check.

$

How it works.

You enroll in a course. The agent picks a problem at your current level. You solve it in main.go, type check, and the agent grades the solution: bumps the concept's level, logs whatever you got wrong, generates review cards from your mistakes, and schedules the problem to come back later. 

$ check
✓ Solved.
Concept hash-maps: L1 → L2
Created 4 review cards.
Re-solve scheduled in 7 days.

When you don't know.

You don't peek at the solution. There is no solution to peek at.

You type I don't know. The agent breaks the problem down: a smaller version, a building block, a sub-problem you can solve right now. You solve it. Then the next one. Then the original.

You never accidentally read the answer. You never give up either.

When you've solved it.

Two things happen. The mistakes you made become review cards — small concept-level questions on their own schedule. And the problem itself enters a Leitner schedule: 7, 21, 60, 180, 365 days.

Leitner schedule: 7, 21, 60, 180, 365 days, with three example problems plotted 7d 21d 60d 180d 365d two-sum-variant hash-maps · step 2 linked-list-cycle two-pointer · step 1 course-schedule graphs · step 4

Seven days later, two-sum-variant comes back. Your old solution is hidden. You re-solve it from scratch.

Clean re-solve, the next due date pushes further out. Need scaffolding, the step holds. Two consecutive failed re-solves on the same concept drop its level by one and the agent reroutes you to easier problems on that concept until it sticks.

Two courses.

Algorithms & Data Structures

35 concepts

Arrays, complexity analysis, hash maps, recursion, trees, graphs, dynamic programming. The interview shapes you actually need.

  • complexity-analysis
  • hash-maps
  • binary-search
  • two-pointers
  • recursion
  • trees
  • graphs
  • dynamic-programming
  • … 27 more

Go Concurrency

31 concepts · race-detected

Goroutines, channels, select, mutex, context. Patterns that pass go test -race. The stuff that trips senior engineers.

  • goroutines
  • channels
  • select
  • mutex
  • context
  • waitgroup
  • channel-ownership
  • race-detected
  • … 23 more

State lives in plain JSON and Markdown files on disk. Switch between Claude Code, Codex, Cursor, OpenCode, Aider, Gemini, or Cline anytime — your progress doesn't move.

Try it.

You need Go ≥ 1.26 and any AI coding agent that reads files and runs shell commands. The make init step checks the version, finds your agent, and enrolls you in a course.

install 

git clone https://github.com/zuzuleinen/algotutor
cd algotutor
make init