Hands-on coding trainer · runs on your machine

AI writes the code.
Make sure your engineers
still understand it.

CodeTrain teaches developers on their own codebase, one tiny step at a time — they type every line, you see they learned it. No autocomplete doing the thinking for them.

Your code never leaves your machine. Free skill on GitHub · Pro from $24/mo.

codetrain — repo mode · src/auth/session.py
# Step 3 of 6 — refresh-token rotation
tutor ▸ Why does verifying the old token before issuing a new one matter here?
you ▸ so a stolen refresh token can't mint a fresh session
tutor ▸ Right. Now write the check — just the guard, not the whole function.
you ▸ if not verify(old): raise Unauthorized()
tutor ▸ ✓ tests pass. Tell me what breaks if you move it after the issue() call.

Cursor and Copilot help write the code.
CodeTrain makes sure your team still understands it — and proves it.

The skill is quietly leaving the building

As AI writes more of the code, the understanding behind it erodes. Juniors ship features they can't debug. Onboarding still takes months. "It works" stops meaning "we know why."

89%

of educators report AI-driven skill atrophy

The discovery phase of learning — where understanding actually forms — gets skipped when the answer is one tab away.

3–6 months

to ramp a new hire on a real codebase

Generic courses teach someone else's code. Your patterns, your standards, your gotchas go untaught.

$200k+

to replace a developer who never ramped

Seniors burn their week answering the same questions. Skill doesn't compound; it leaks.

Learn by doing — on the code that matters

No videos, no toy exercises. A Socratic tutor that asks, nudges, reviews your submission, and runs the tests — but never hands you the answer.

Point it at your repo (or a sandbox)

Repo mode edits land in your real branch, so finished code is just part of your work. Sandbox mode is a throwaway project for practice. Either way it runs on 127.0.0.1 — your code stays local.

Write each step yourself

The tutor breaks the work into tiny steps in a real editor with an instant Run button. You type the line; it reviews what you wrote and explains what changed.

Get nudged, not spoon-fed

Stuck? It shrinks the step or reveals the next hint — never the solution. Failing code is the best teaching moment, so it leans in instead of bailing out.

It remembers you

A small local profile tracks your level, streak, and recurring gaps — and resurfaces what you struggled with later (spaced repetition). Sync it across machines on Pro.

Not another autocomplete

Your live codebase

Trained on your repo and standards — not generic katas (Codecademy, Scrimba) or someone else's curriculum.

You type every line

Hands-on by design. Reading an explanation isn't learning; producing the code is. That's the difference from AI explainers.

Code never leaves the box

Local-first agent. Bring your own Anthropic key for enterprise and nothing but a license check touches our servers.

For engineering teams

A free tutor helps one dev. A team needs to standardize and measure understanding — onboard everyone on your codebase the same way, and prove it stuck.

Onboarding that compounds

Curricula built on your repo + standards. New hires ramp in weeks, not months — without tying up your seniors. Track who's ramped and where they're stuck.

Skill-health you can show the CTO

Dashboards and skill-gap heatmaps turn "we did some training" into evidence. SSO, BYO-key, and self-host keep security and procurement happy.

Pricing

Start free. Upgrade when you want your real repos, your own model key, or your whole team. No card to start.

Free
$0
Start free
Pro · most popular
$24 / mo
  • Your real repos (repo mode)
  • Fair-use sessions, zero setup
  • Cross-device profile sync
  • Bring your own key (optional)
Get Pro
Team
$32 / seat/mo
  • Everything in Pro
  • Onboarding + skill dashboards
  • SSO & central billing
  • Bring your own key
Choose Team
Enterprise
Custom
  • SSO / SCIM, audit logs
  • VPC / self-host, SOC 2
  • Code never leaves your env
  • Onboarding-ROI pricing
Talk to sales

Questions, answered

Does my code get uploaded anywhere?

No. The agent runs on your machine and serves the UI on localhost. On the managed plan, only short prompt snippets go to the model. On Bring-Your-Own-Key (Team/Enterprise), model calls go straight to Anthropic with your key — nothing but a license check touches our servers.

Isn't this just ChatGPT explaining my code?

The opposite. Explainers do the work for you. CodeTrain makes you write every line, reviews it Socratically, runs your tests, and tracks what you didn't get so it can resurface it. You finish able to do it without help.

We already use Copilot / Cursor. Why this too?

Those make your team faster at producing code. This makes sure they still understand it — and gives you a way to prove ramp and retention. Different job. They're complements, not competitors.

What does "bring your own key" mean?

You connect your own Anthropic (or Bedrock) API key. Your code and prompts go directly to the model on your account — best for security and cost control — and we just provide the software, accounts, and dashboards.

Is there really a free version?

Yes — the core tutor is a free, open skill you can run today. Paid plans add zero-setup managed access, your real repos, cross-device sync, and the team layer.

Stop shipping code your team can't explain

Spin up a session on your own repo in two minutes. Free to start.