🚲 Tandem

the terminal is the new classroom

Learn vibecoding
in the passenger seat.

Building with AI agents is a practice, not a syllabus — you learn it the way you learn to drive. Tandem puts you in a live terminal with someone who already ships with Claude Code: watch them work, then take the wheel while they’re beside you.

room: checkout-fixJaime is driving
jaime@tandem $

The apprenticeship loop

Software skill has always transferred by watching, then doing with someone beside you. AI agents made the expert’s screen the scarce resource again — Tandem shares it.

I do

Watch

Your instructor drives their agent on a real task while you watch the terminal live. The failures are the lesson — and nothing is edited out.

We do

Drive together

Control passes to you mid-session. You phrase the prompts; the instructor watches, corrects, and takes back the wheel when things go sideways.

You do

Fly solo, reviewed

Run your own session. The transcript captures every prompt you wrote, so your instructor can review how you think — not just what you shipped.

A classroom that’s actually a terminal

No slides, no sandboxes, no edited screencasts — a real agent, on a real machine, working on a real codebase, shared live.

👀

Watch a real operator work

The instructor’s agent runs on THEIR machine — Claude Code, Codex, any CLI. Tandem streams the real terminal to your browser: every prompt, every correction, every recovery, unedited.

🎛

Take the wheel

One driver at a time, by design. The instructor demonstrates, then hands you the keyboard — you drive the agent yourself while they watch and step in when you wedge.

💬

Ask beside the terminal

Chat sits next to the session, so questions never interrupt the flow. Drop files and screenshots straight into the agent’s working folder.

📜

Every lesson becomes a transcript

Sessions record automatically. Browse what was typed — the exact prompts, the wrong turns, the fixes — any time after the session ends.

Real codebases, not sandboxes

Git branch, dirty state, ahead/behind — visible to everyone live. You learn on real projects with real stakes, not toy exercises.

🔒

Local-first, key-safe

The bridge makes an outbound-only connection from the host’s machine. API keys, dotfiles and repos never leave home.

Live in three steps

1

Host starts the bridge

One command from the dashboard puts the host’s terminal in a room. Outbound-only — no ports, no VPN, no firewall fights.

tandem.duosh.dev/app → + New terminal
2

Learners join by link

Send the room URL. Students sign in with GitHub and are watching the session in seconds — nothing to install.

relay.duosh.dev/?room=…
3

Teach, hand off, review

Chat, pass control, drop in files. When the session ends, the transcript is already in the library.

📜 transcript saved

Pricing

Learning is always free — only hosts pay. Invite someone new and you both get two weeks of Pair free.

Free

Learn by watching

$0forever
  • Join any session you’re invited to
  • Solo sessions with your own agent
  • Automatic recordings & transcripts
  • Your personal session library
Start free
Most popular

Pair

1:1 teaching & mentoring

$20per host / month
  • Everything in Free
  • Host live shared sessions
  • Students join free with a link
  • Control handoff, chat & file sharing
  • Git-aware presence
Start teaching

Team

Cohorts & classrooms

$30per seat / month
  • Everything in Pair
  • Organise sessions into projects
  • Channels for each cohort
  • Seat & member management
  • Shared session library
Run a cohort

Billing launches with the beta — early users keep free access until it does.

Questions

Why learn this live instead of from videos or courses?

Working with AI agents is judgment, not syllabus — when to re-prompt, when to interrupt, when to revert. Courses go stale at every model release; an edited video hides the recoveries, which are the actual lesson. Watching a live session — then driving one — is how the skill transfers.

Does my code or my API key go through your servers?

The agent runs on the host’s machine; only the terminal stream (what you’d see on screen) relays through the hub, encrypted in transit. API keys, dotfiles and repos stay local.

What tools does it work with?

Anything that runs in a terminal. It’s tuned for AI coding agents — Claude Code first — but a plain shell, vim, or any REPL streams just as well.

Do students have to pay?

No. Joining a session is always free with an account — only the host needs Pair or Team. And when you invite someone new, you both get two weeks of Pair free.

I just want to pair with a teammate — is Tandem still for me?

Absolutely. The teaching flow IS the pairing flow: live shared terminal, control handoff, chat, transcripts. Pair is pair programming; Team is your team’s pairing home.

What happens to recordings?

They’re private to you (or your cohort) by default. Browse the transcript, share deliberately, or delete — deletion is real deletion.

The fastest way to learn this is beside someone who already can.

Open Tandem

🚲 Tandem — a duosh.dev project · Your terminal stays yours.