Autarkby Teydra Lab Download
A Meta Jarvis project · by Teydra Lab Version 0.3.2 · Free download

Autark: Your own AI company. It doesn’t wait for a prompt.

A manager, specialist agents and a secretary that pick up work, split it up, finish it and report back — on your own computer, with the ChatGPT and Claude plans you already pay for.

No accountNo subscription from usYour data lives on your PCAlso for macOS and Linux
You
YouOwner
T
TheoSecretary
M
MaraManager
Ana
AnaColleague
I
IvoResearch
L
LenaMarketing
N
NoaFinance
K
KaiWeb
HumanAI agentWorking
Tue 09:00

Illustration: you hand one task to your manager agent Mara. She splits it into four tasks for research, marketing, finance and web agents. The finance agent asks your colleague Ana a question in the chat and you read along. Your secretary moves a call on its own. At the end Mara sends you a briefing.

01 The problem

AI got brilliant. It still waits.

The most capable models ever built sit behind an empty text box. They answer when asked, forget when you close the chat, and leave the real work, the routing, the follow-ups, the copy and paste, to you.

A / Reactive

It waits for you.

Nothing happens until you type. A chat assistant does not notice the email that needs an answer, the deadline tomorrow or the task that stalled at 3 pm.

B / Forgetful

It forgets.

Every new chat starts from zero. Goals, promises and half-finished work live in your head, not in the system that is supposed to help you.

C / You are the glue

You do the routing.

You copy from the mail into the chat, from the chat into the doc, from one assistant to the next. The AI does the parts. You are still the operating system.

D / Unused

Your plan expires unused.

You pay for ChatGPT or Claude every month. Weekly limits reset whether you used them or not, and most of what you paid for was never asked to do anything.

02 The idea

The idea behind Autark

You write it in.
It gets done.
It gets ticked off.
It gets documented.

„ich schreibe Sachen rein, es wird erledigt, es wird abgehakt, es wird dokumentiert.“Stanislaus Hees, the original brief
03 How it works

Say it once. Your company takes it from there.

Autark is not another chatbot. It is an organisation: a manager who routes the work, specialists who do it, and you, who are asked only about what really needs you.

01 — Work

Say it once.

Type or dictate into one inbox. Your manager can split a long sentence into separate tasks, each with the right owner: an agent, or your own My day.

02 — Agents

Your team does it.

Agents delegate among themselves, open your apps, browse, read files and write things down. The steps land in a run journal you can read.

03 — You

You say how far it goes.

The first thing your manager asks is how far it may go. That is a question, not a barrier: agents have full access from the start. Your answer steers them, and so does every message after it.

04 Proactive

Close the window. The company keeps working.

22:40Theo sorted 31 new emails and drafted 4 replies
23:15Ivo finished the research report on six competitors
00:30Kai fixed two broken links on your website
01:10Lena wrote three post drafts for this week
02:05The heavy work ran on the plan that resets tomorrow
03:20Noa has a question about a €640 invoice
06:45Theo planned your day around three meetings
Morning briefing07:30
Good morning. Here is what happened while you slept.
6Tasks done
1Needs you
0Problems

Noa has a question about the €640 invoice. Everything else is in My day.

22:00
07:30

An illustration of how a night can look, not a measured run.

While your computer is on, agents wake up on schedules, timers, messages, tasks and events, even with the window closed. They can plan their own follow-ups, and in the morning you get a briefing of what was done and what needs you.

05 Engines

Runs on the AI you already pay for.

Autark is not another AI subscription. Your agents work through the official tools of each provider, with your own accounts. Add as many accounts as you like; Autark picks the engine, the model and the effort for each turn.

ChatGPT planvia OpenAI Codex
LLena · working62 % left · resets in 2 d
Available
Paid Claude planvia Claude Code
IIvo · working35 % left · resets in 5 d
Available
API keysa dozen known · any server by address
pay per use · optional
Early
Local modelsOllama · LM Studio · llama.cpp · vLLM
runs on your hardware · optional
Early
Gemini CLI · Copilot CLI · Kimi Codeover the Agent Client Protocol
built · never seen in a live run
Early
Switch engines mid-task. The agent’s session is rebuilt from a shared context ledger, so nothing has to be explained twice.Use it before you lose it. The plan that resets soonest goes first.

Quota numbers above are example values. API keys and local models have no recorded live run yet.

06 Capabilities

Everything a company needs. Nothing you have to wire.

Chats, tasks, a calendar, your apps, your inbox, a browser, a secrets catalog, your phone. Each piece is labelled honestly: what is in today’s release, and what ships next.

All 68 capabilities

Available

Work: one inbox for every task

Type or dictate. With Auto your manager takes it, decides who does it and can split it into separate tasks. Or pick an agent yourself, or Me for your own to-do list.

Available

Wake-ups and routines

A message, a task, a timer, a schedule or an event wakes an agent. It decides what to do, does it, and can plan the next step itself.

Available

My day

Your own to-dos and calendar in one calm list, with learned time estimates, a morning plan and a short briefing of what happened.

Available

Chats and group chats

Every agent has a direct chat; add groups and as many chats per agent as you like. You can keep typing while agents work; a message marked important steers work that is already running.

Available

Connected apps

MCP servers in one file, connectors/mcp.json, in the same format Claude Code and Cursor use. Agents find a server and write the entry themselves; the tools appear within a second.

Available

Email

Your own mailbox over IMAP and SMTP with an app password (Gmail, GMX, iCloud and others). A new mail can wake an agent. Outlook and Microsoft 365 are not supported yet.

Available

Computer use

On Windows agents prefer real UI automation over raw clicks, and your own mouse and keyboard win. On Linux it runs over AT-SPI, with input on X11 only. On macOS agents get screenshots but cannot control the computer.

Available

Secrets by ID

Passwords and keys are encrypted with your operating system’s protection. Agents work with IDs like secret://github, values stay out of prompts, and known values are masked in tool output. Every secret works everywhere; none is tied to a site.

Available

Your phone

Off until you turn it on. Scan a QR code and your PC serves the app to your phone in its browser, over Wi-Fi or Tailscale. No app store, no cloud account.

Available

Several PCs

Pair your computers over the local network, a Remote ID or an address, compare a code, and let agents work on the machine that has the files.

Available

Search by meaning

Memory and any folder an agent chooses become searchable by meaning. A small local model does this on your PC, or an embedding provider you pick. Office documents can be read too.

Available

Dictation and calls

Dictate instead of typing. Call an agent inside a chat, optionally with OpenAI Realtime and your own key. Early.

07 Open

No connectors to wait for. Files your AI can change.

Settings, providers, skills and memory are plain files on your disk. So the AI can add a provider it has never seen, write a skill or connect another app by itself, and you can read every bit of it.

Available

A short start

Connect one AI, type your name and company, press Start. The manager gets to know you and your work, and first asks how far it may go on this PC.

Available

A browser per chat and per agent

Three places: the global browser where you work, a browser for each chat with tabs everyone in that chat shares, group chats too, and each agent’s own, which you can watch. Agents working in the background do not disturb your tabs.

Available

Providers through a file

Every API connection is one entry in settings.json: a name, an address, a protocol, a key as an ID. A provider the app has never heard of works if it speaks one of the protocols. Say the provider’s name and hand over a key; the AI can write the rest.

Available

Skills as open files

A skill is a folder with a SKILL.md, the format other agent tools use too. Each has a route: an agent’s own, its managers’, shared or built-in. The AI can read skills from folders of other tools when it chooses to, and writes new ones itself.

Available

Memory as open files

One Markdown file per memory, in folders for the company, a branch or a single agent. Open them, change them, version them. Any change is searchable at once.

Available

The AI builds its own connections

There is no WhatsApp button. Your agent sets it up: a small script next to the app, using the running app’s own interface. Telegram works the same way with a bot it creates. Other channels, such as Signal or Matrix, are the same kind of script: skills ship for WhatsApp and Telegram, and one that shows how for any other channel.

How the open system works

08 Access

It can do everything. You say how far it goes.

Agents run with your rights, without a sandbox or approval prompts. There is no guardian and no money limit in the app. Text steers them.

The first question

The first thing the AI asks is how far it may go: full access for good, this one search just this once, or less. It is a question, not a technical barrier.

Secrets by ID

Agents use secret://… references. Values stay out of prompts, and known values are masked in output.

Backups on your disk

A copy of the data folder when you ask for it, and a copy of the database before each update. They do not undo what an agent did elsewhere.

A brake

“Stop all agent work” or Ctrl Alt Shift X halts every agent on this PC and stays stopped after a restart.

What that means, plainly

Illustration: an agent’s actions go directly to your PC, to the web and your accounts, and to what steers it: your words, skills and memory. Nothing stands in between.

09 Local-first

Your company lives on your computer.

No account with us. No cloud of ours. Chats, tasks, memory, agents and the secrets catalog sit in a folder on your own disk. Prompts go to the providers you connect.

  • Phone access as a web app served by your PC
  • Several PCs, over your network or Tailscale
  • Backup, restore and your chats as files
10 Where it fits

Not a chat. Not a workflow. A company.

Chat apps answer. Automation tools follow fixed rules. Agent frameworks are parts for developers. Autark is the finished organisation in between.

What you getAutarkChat apps
ChatGPT, Claude
Automation tools
Zapier, n8n
Agent frameworks
CrewAI, LangGraph
Starts work without a promptYesPartlyYesPartly
A team with roles and delegationYesNoPartlyPartly
Runs on your existing ChatGPT or Claude planYesYesNoNo
Your data lives on your computerYesNoPartlyPartly
Acts in your apps, browser and filesYesPartlyYesPartly
Settings, skills and memory as open files the AI can changeYesNoPartlyPartly
A finished app, no codeYesYesPartlyNo

Categories, not single products; individual tools differ. Based on public product descriptions, November 2026. Detailed comparison

11 Status

Early. And honest about it.

Autark is young and moves fast. Here is what you get in today’s release, what is built and ships next, and what is still planned. What is not proven yet has its own list.

AvailableVersion 0.3.2
  • Manager, teams and a secretary
  • Chats and group chats
  • Work: one inbox for every task
  • My day
  • Wake-ups and routines
  • ChatGPT and Claude plans
  • Memory as open files
  • Connected apps
  • Email
  • Secrets by ID
  • The AI builds its own connections
  • Your phone
Planned
  • Outlook and Microsoft 365 mail
  • Computer control on macOS
  • Signed installers
  • Published source code

Start your company.

Download for Windowsv0.3.2 · 132 MB
Released 2026-11-05Free · no accountWindows, macOS, Linux

You need at least one AI: a ChatGPT plan, a paid Claude plan, an API key or a local model. The builds are not signed: Windows SmartScreen asks you to confirm (“More info” → “Run anyway”), and macOS needs a few extra steps. See what you will see.

12 Questions

Asked often.

All questions

What is Autark?

Autark is a desktop app that gives you your own AI company: a manager, specialist agents and a private secretary. You talk to them in chats and drop tasks into one inbox. They pick up the work, delegate it among themselves, finish it and write it down, and they wake up on their own when something needs doing.

Is it free?

Yes. The app is a free download with no account and no subscription from us. The AI work runs on the plans you already have (for example a ChatGPT or Claude plan), on your own API keys or on local models, so you pay your AI providers directly.

Which AI subscriptions does it use?

ChatGPT plans through OpenAI Codex, and paid Claude plans through Claude Code, both via the official command-line tools of each provider. Gemini CLI, GitHub Copilot CLI and Kimi Code are built in too, but we have never seen them in a live run. The Claude Free plan cannot run agents.

What can agents do on my PC?

Everything your user account can. Agents run without a sandbox and without approval prompts: they can read and change your files, run commands, use a browser and every secret in the catalog. The first thing the AI asks is how far it may go, and that is a question, not a technical barrier. If a PC holds something you cannot risk, give the app its own Windows user or a virtual machine.

Can agents spend money or delete things?

Yes, technically. There is no money limit and no approval gate in the app. How agents weigh a purchase is written in a skill with reference points such as about 20 euros, and the rules ask them to check target, amount and recipient once before something they cannot undo. That is guidance you can edit, not a lock. An agent can pay with anything it can reach, such as a card you saved in the catalog or a shop where its browser is logged in.

Does my data go to your servers?

No. There are no Autark servers and the app has no analytics. Chats, tasks, memory, agents and the secrets catalog live on your own computer. Everything an agent works with goes to the AI provider you connected, including private files if it opened them. The access page lists every other place something leaves your PC.

Do agents keep working when I close the window?

Yes. By default the app keeps running in the system tray, and agents wake up on schedules, messages and events as long as your computer is on.