Does my code get uploaded anywhere?

The agent loop, your files, and your project memory stay on your machine, and your API key never leaves the app. What an agent puts in a prompt does go to DeepSeek, under your own key — that's how any hosted model works. The difference is that there is no AutoCoder server in between, so we never see your code or your key.

What will this actually cost me per month?

Two things, and you should count both: the subscription (₹0 on the free tier for 50 queries, ₹899/month for unlimited) plus your own DeepSeek token spend, billed directly by DeepSeek at their rates. A typical task on V4 Flash lands in the low single-digit cents. Run /total_cost in Telegram at any time for the running total.

Do I have to leave my computer on?

Yes — and awake. AutoCoder runs the orchestrator in-process on your desktop; Telegram is the remote control, not the runtime. Tasks you send from your phone queue on that machine and execute there, so if it sleeps or you shut the lid, the run pauses until it wakes. Before scheduling anything overnight, set the machine not to sleep. That's the honest trade for keeping your code and your key local — there is no cloud runtime to fall back on.

Which platforms are supported?

Windows desktop today, via the Microsoft Store. It's a young project — if you're on macOS or Linux, the honest answer is "not yet."

Do I need my own DeepSeek API key?

Yes — it's required, not optional. You paste it into the app once and pay DeepSeek list price directly. We don't resell tokens, bundle credits, or take a cut, which is why there's no markup to explain.

What happens when an agent gets it wrong?

Two of the five agents exist for exactly that: the Verifier runs typechecks, tests, and local Semgrep packs and loops back on failures, and the Reviewer produces line-level findings with severity levels. You still get a grouped diff to read before anything ships. And /cancel stops a running task from your phone.

Can I keep it from doing things I don't want?

Persistent project rules live alongside the repo and are re-read on every task, so conventions stick without repeating them in each prompt. You also control the thinking budget — how many tokens the model may spend reasoning — and whether a task runs on all five agents or just one.

The reviewer emits structured JSON with per-line annotations, severities, and fix suggestions, which GitHub Actions, GitLab CI, and Jenkins parse natively. Scheduled tasks can create or update a PR with a grouped diff when they finish.

Why not just use Claude Code or Cursor?

Often you should. They're pair programmers — excellent when you're at the keyboard, reviewing as you go, with stronger models behind them. AutoCoder is for the other case: work you want to hand off entirely. If you want to be in the loop on every edit, use theirs. If you want the work done while you're doing something else, use ours.

Is the 6-digit access key safe?

It rotates every 7 days automatically, and you can force a new one at any time with /access_key. It authenticates your desktop app to your own Telegram account — it is not your DeepSeek key, which never leaves your machine.

Can I write prompts in a language other than English?

Yes — prefix a prompt with @regional and you'll get research-backed answers in 22 Indian languages, at the same price as English. No surcharge, no separate tier.

Back to AutoCoder.dev

A narrow bet on handing work off

Most AI coding tools are built for the moment you are at the keyboard. They are pair programmers, and the good ones are very good: you review as you go, you stay in the loop, you catch things early. That is a real workflow and it deserves the tools it has.

AutoCoder is built for the other moment — the ticket you would rather not sit through. You send it from Telegram, you go and do something else, and five agents discover, plan, execute, verify, and review it on your own machine while you are gone. What comes back is a grouped diff and the exact cost of the run.

That is the whole thesis. It means we are worse than a pair programmer at being a pair programmer, and we would rather say so than pretend the two things are the same product.

What we won't claim

That your code never touches a server. The agent loop and your files are local, and we never see your key — but prompt context goes to DeepSeek's API under your own key, because that is how any hosted model works.
That you can close the laptop. The orchestrator runs in-process on your desktop. If the machine sleeps, the run pauses. Walk away, yes; shut it down, no.
That we are the only tool that does this. We're not. Anthropic ships Telegram control for Claude Code, and several other projects work in this space. We think the fully-autonomous, bring-your-own-key, runs-on-your-hardware combination is a genuinely different shape — not that nobody else is nearby.
That it is finished. Windows only. No macOS or Linux build yet. It is a young project and the roadmap is shorter than we would like.

Talk to us

Bug reports, disagreements about the roadmap, and “this claim on your site is wrong” emails are all welcome at support@autocoder.dev. The last category gets answered fastest.