Your own AI that gets real work done

Toss DeTars one line. It runs the rest.

For the personal work that takes more than one chat.

Hoursit works unattended · even overnight
Allthe major models · switch anytime
100%what it knows stays on your machine

· Every claim here is one you can check on your own machine — not slide-deck rhetoric

Why now

Today's model is a brilliant but unreliable intern.

Dazzling in flashes — but it forgets, fakes completion, and crashes halfway. Nobody hands real work to something unreliable. DeTars turns it into a team you trust with the real thing.

Living with it

You send one line. It comes back done.

1
Input from anywhere
Telegram / Slack / Feishu — one line or one photo (WeChat: text only)
2
It runs in the background
Hours, even all night — you don't babysit it
3
It comes back to you
It lives for you — not the other way around.
📷Pet Care
via Telegram
Snapped a photo of my dog and sent it over
editing · writing captions
✓ Funny short video + social captions ready
detars · pack: pet-care
One motif: input → runs in background → comes back
The store

Apps that are useful, fun, and yours alone.

The person you have always wanted to meet. The opportunity you saw coming and didn't hold. The thing you wanted to understand, where everything you found was copied from everything else. An unfamiliar, enormous codebase. Something you want to say, that shouldn't cost you three days. Each one is a whole app — and each one is a Tars, willing to go through the black hole with you.

Why you can trust it
01

It thinks for itself

Give it a goal — ‘research three competitors this quarter, deliver a sourced report.’ It breaks the work down, spins up specialists, tracks their progress, and hands back a finished draft. The how is reasoned on the spot, not a hard-wired script.

orchestrator.loglive
plan goal → 3 subtasks
agent A · filings
agent B · news
agent C · cross-check
pause · await A/B → merge
Real: it forms teams, splits work, pauses and resumes — actually running, not faked.
02

It doesn't fall over

Real work runs for hours: flaky networks, rate limits, sleeping laptops. Most tools lose hours to a single hiccup. DeTars treats trouble as a fact — back off, retry, continue; reboot and it resumes. Let it run overnight; check results in the morning.

runtime.recovery03:14
429 rate limited → backoff
✓ recovered, resuming step 7
sleep checkpoint saved
✓ resumed from checkpoint
Real: errors are facts to route around, not instant death.
03

It can't fake it

AI's worst trick: swearing it's ‘done’ when it isn't; citing a source that never existed. DeTars makes ‘done’ a receipt it must honor — delivered or not, backed by evidence or not. Every citation is sealed; change one character and it's instantly void.

completion.receiptverified
deliverable ....... ✓ present
evidence chain .... ✓ complete
sha256: 9f4c…a1e
peer review ....... ✓ signed
citation altered → rejected
Real: ‘done’ is a verifiable receipt, not a feeling.
04

It's yours — and no one can take it

It lives on your own machine and learns you over time. But everything it remembers about you needs your nod first; that memory is a file on your disk, not an account on someone's server. No one can brick it with a notice the way Rewind or Humane did.

~/detars/memorylocal
./profile.mem
./projects/*.mem
new memory → awaiting your ok
✓ works offline · nothing uploaded
Real: memory and identity are files on your disk — sovereignty baked into the architecture.
05

It evolves itself

It hunts its own bugs into permanent regression coverage, reorganizes its own memory, and — when a task needs a capability it lacks — generates, installs, and manages its own tools and skills. Every version is harder to beat than the last.

evolution.logauto
regression +1 case sealed
memory reindexed
skill needed: pdf-extract
↳ generated · installed · ✓
every version harder to break
Real: reliability that compounds — and new abilities it grows on its own.
06

It doesn't burn your budget

Long unattended tasks usually mean huge bills. DeTars routes to keep the model's KV / prompt cache hot, so repeated context isn't paid for twice — far fewer tokens per task, and cheaper as model prices fall. Let it run all night without watching the meter.

routing.cachelive
context 184k tokens
↳ prompt cache · hit
billed → new tokens only
repeat context: not re-billed
Real: caching-aware routing — fewer tokens billed, no runaway bills.
0
lines of code · written in six months

We don't just say it can do hard work — it produced itself.

Several million lines of code, and half of it was written by the product itself. It is both an app and the ground you stand on. What you build up on it this year won't be written off next year because a different company won.

DeTars is your permanent third-party terminal.
Yours, not rented.

A private AI team you own — always on, commandable from any chat window, and one that comes back to you on its own.