Human.01

Everyone else says bring your own AI.
We say bring nothing.

Press Launch and get your own computer in the cloud in seconds, with an AI agent that builds for you and a Bot that drafts replies to your chats. 10 million AI tokens a month are free, with no account, no credit card and nothing to install.

Opens right here in your browser, straight into the AI agent.
vm.human01.org/box

Start on a free box, right now

  1. 1

    Run one command

    Any terminal on Mac, Linux or Windows. No account, no credit card.

    $ ssh vm.human01.org

    No SSH key yet? Run ssh-keygen -t ed25519 and connect again.

  2. 2

    Build with the AI agent

    Your own Linux computer opens in seconds. Type agent and tell it what to make: 10 million AI tokens a month are free.

  3. 3

    Claim it to keep it

    A free box gives you 60 minutes to build. Claim it with your email and it stays yours; a box nobody claims is deleted after 24 hours.

What will you make?
Pick one and try it.

Choose who you are, then press Try this. Your box opens with the first step already written for you, and you press Start.

A real machine,
not a shell account.

Every box is a hardware-isolated virtual machine with its own Linux kernel - not a shared container. Break things freely.

1vCPU

One virtual core and 2 GB of RAM on Free, enough to build, test and run real projects. Paid plans get 2 vCPU and 4 GB.

10GB disk

A private home directory that persists for as long as your box lives.

~4seconds

From pressing enter to a prompt. Boxes boot on demand, no queue and no signup.

Ready to build

Debian 13 with the essentials installed, plus an AI coding agent: type agent to start opencode, already connected to Human.01 AI.

box@3f9a12c0:~/app
$ agent --version && ls /usr/local/bin
node 22python 3.13gitghmisetmuxvimcurlgccopencode (AI)

One tab holds it all,
on any screen.

Launch opens your box right in this page: the agent, a terminal, your files and the Bot, one tap apart. It works the same on a phone.

Four tabs

The AI agent (opencode) opens first. Switch to a normal terminal, your files or the Bot, and the agent keeps working.

AgentShellFilesBot

Files and a code editor

Browse your project, edit code in a real editor, upload files or drag and drop them in. Paste an image, audio or file straight from your clipboard.

A live status bar

Connection, time left, images left, whether your app is running, git, RAM and load, and disk, always at the bottom.

Open your app

Run your app on $PORT and open it at its own address. It is private to you until you claim the box.

<boxid>.vm.human01.org

GitHub auto-save

Connect GitHub in about a minute with a device code, with help to sign up if you have no account. Every change is then saved to a private repo about a minute after you stop.

Files such as .env, keys and node_modules are never uploaded.

Your own terminal

A one-time pairing code links your laptop's ssh key to this same box. Then ssh vm.human01.org opens it from there.

On your phone

The workspace works on a phone screen, and you can install it as an app.

Four languages

Pick one at the top of the page. The terminal, the claim email and the Bot follow your choice.

English简体中文繁體中文Bahasa Melayu

Your box comes with
an AI engineer.

Type agent and start building with opencode, already connected to Human.01 AI. No API keys, no setup, nothing to install.

10Mtokens a month

Every account gets 10,000,000 tokens of Human.01 AI a month, free, metered the way Claude and Codex do it: a 5-hour session and a rolling week, each with its own cap, shared by all your boxes. Pro gets 60,000,000.

128kcontext

Qwen3.8 Flash Next 180B runs on our own A100 GPUs and works with up to 128k tokens of your chat and code at once.

30a minute

Fair use keeps it quick for everyone: up to 30 requests a minute, 3 at a time.

19free models

From OpenCode, Kilo Code and OVHcloud. They are shared and rate limited, and they don't count against your 10M a month.

Build with an agent

opencode reads, edits and runs code inside your box. Describe what you want, watch it work, and keep the result.

Code search

The agent has a search tool that finds the right code in your project quickly, instead of reading every file. Very large projects fall back to grep.

search_code

Generate images

Ask for a hero image, illustration or background and the agent saves a PNG straight into your project, made by Qwen-Image on our own GPUs.

text to image6 per hour20 per day

Design that isn't generic

A built-in frontend design skill pushes the agent towards distinct typography, colour and layout instead of the same template every time.

frontend-design

See what your AI spends

The gauge button in the workspace opens your AI usage: how much of your 5-hour session and of your week is used and when each resets, updated live while the agent works.

Live, call by call

Session and week as two bars, today's tokens broken down by model, and the last calls the agent made.

Worth changing

It spots wasted context, such as the same part sent twice or a part that is far too big. Each finding has a button that copies a message for the agent.

It only watches

The watcher never changes a request. It only observes, and you can switch it off.

Models you can choose

Human.01 AI is the default. The free models below are one keystroke away: press ctrl+p in the agent and pick a model.

Human.01 AI

The default. Runs on our own A100 GPUs with a 128k context, and every account gets 10,000,000 tokens a month free.

Qwen3.8 Flash Next 180B

OpenCode free for a limited time

Three fast models, offered free by OpenCode. None of them train on your prompts. DeepSeek and GLM keep no prompts; Beam keeps them for 30 days for safety.

DeepSeek V4.1 FlashGLM-5.3-FlashBeam

Kilo Code free

Seven free models, including very long context.

Nemotron 3 Ultra 550BNemotron 3 Super 120BNemotron 3.5 LightningCohere North Mini CodeDots 3 Note PreviewOpenRouter FreeKilo Auto Free

OVHcloud free

Nine open-weight models hosted in the EU.

Qwen3.5 397Bgpt-oss 120Bgpt-oss 20BLlama 3.3 70BQwen3.8 27BQwen3.6 27BQwen3.5 9BMistral Small 3.2 24BMistral Nemo

The free models come from outside providers. Everyone using Human.01 boxes shares their rate limits, so they can be slow or busy at peak times, and the providers may log prompts. Keep secrets out of them.

Just ask.
The agent does the rest.

No commands to learn. Type what you want in plain words, and use the shortcuts below. Pick any example to watch it.

Example

      
These are examples of what the agent does. Your results will look different, and that is the point.

Your chats, answered.
You still press Send.

The Bot is an assistant that reads your chat apps on its own computer screen in your box and drafts the replies. You check each one and press Send.

Its own screen

The Bot works in a real browser inside your box. Watch it live, and take control whenever you want.

Your chat apps

WhatsApp works directly. Telegram, WeChat, LINE and Messenger are read from their own web pages, with a screen reader as fallback. You sign in with the app's QR code on the Bot's screen.

WhatsAppTelegramWeChatLINEMessenger

You press Send

It writes a draft for each reply and waits for you. Automatic sending is off unless you switch it on.

Some things always wait

Payments, codes and private matters always wait for you. Add your own rules in plain words.

Teach a task

Do a task once while it watches, and it can repeat it, for example every morning.

Schedules, memory, library

Set a job for a number of minutes from now, daily, on weekdays or weekly. Its memory lasts, and your own documents become its library.

PDFWordExcelPowerPointHTML

Jobs from your phone

Send a command, a photo or a file to your own WhatsApp chat (Message yourself). It does the job and answers there, and can even write and run code in your box to get it done.

See what it did

A log of what it did, its drafts and its stats, so nothing happens out of sight.

20replies free

Every box can try the Bot with 20 sent replies, free.

10an hour

At most 10 replies are sent in any hour. The Bot uses your box's daily AI allowance.

Take the app apart.
See how it really works.

A LAB box trades the Bot for a reverse engineering workbench. Ask about an app and the agent inspects the real thing, then shows you the evidence behind every answer.

Desktop and web apps

Electron and .NET apps, Go and Rust binaries, websites and saved captures. The agent reads the code and explains the behaviour it finds.

Electron.NETGoRustWASM

Down to the binary

Ghidra, JADX and apktool come installed. No licence to buy, no setup: the agent drives them and reports back with the code it read.

GhidraJADXapktool

Your Android phone

Plug it into your computer and the box can reach it. Pull an app off the phone, take it apart, then build a new version and put it back.

adbWebUSBAPK

Live traffic

Watch requests pass through your box as they happen, then hand the whole capture to the agent and ask it to explain the protocol.

mitmproxytsharkHARpcap

Heavy builds run elsewhere

Compiling and signing an app runs on GitHub Actions, not in your box, so the box stays quick and the build gets a real machine.

Evidence, not guesses

Every finding names the file and the line it came from, and says plainly what it could not determine.

LAB is for lawful research, education, interoperability, software preservation, and analysis of software you own or are authorised to examine.

How businesses use Human.01.
One business, one box, one film.

Each film follows one business and the job its box does for it. Watch how it works, then try the same in your own box.

CAMERA WATCH

A shop asked one question.

"Can my cameras tell me when a shelf runs empty?" Their box set it up in one ask. The same cameras can also watch the back door, the queue, the chiller and more, from one sentence each. Works on the free plan too.

Watch the film
PRINT

Say it. Shape it. Slice it. Print it.

Describe the part and the agent designs it in real millimetres. The box slices it and sends it to your own printer.

Two more boxes on the bench.
Watch them before they ship.

Each one is a film today and a box next. Join a waitlist and you are first in when it opens.

BENCH

Your oscilloscope, live in the box.

The agent writes the firmware, flashes your board over USB, and watches the signal on your scope with you.

CLASS

See every screen. Step into one.

For coding teachers: every student's editor on one wall, the stuck ones flagged, and you step in to point and talk.

Free to start.
Always on when you need it.

Every plan includes the AI agent. Free boxes pause after a day idle; paid plans keep your box running with more room and more AI. Prices are per month in US dollars.

Free

Students and hobbyists
$0
  • 1 box - 60 minutes to build, claim it by email to keep it
  • 1 vCPU / 2 GB RAM / 10 GB disk
  • Sleeps after 24 hours idle
  • Free AI: 10M Human.01 AI tokens a month, plus free models
  • 6 images an hour, 20 a day
Start free Watch: a PDF becomes a PowerPoint

Basic

One project that stays online
$20/month
  • 1 always-on box
  • 2 vCPU / 4 GB RAM / 15 GB disk
  • Kept for as long as your plan is active
  • Your own domain
  • Limited AI with a small monthly credit allowance, 60 images a day
Join the beta

Pro+AI

Heavier AI use
$60/month
  • 1 always-on box
  • 2 vCPU / 4 GB RAM / 25 GB disk
  • Your own domain
  • 6× the AI: 60M Human.01 AI tokens a month (2M per 5-hour session), plus credits for premium models through the Human.01 gateway (credits launch during the beta)
  • Priority AI queue, 300 images a day
  • Helpdesk toolset: a team inbox, a chat widget for your website answered from your own documents, and a help centre - switch it on from your profile (the box grows to 4 vCPU / 6 GB)Watch the Helpdesk video
Join the beta Watch the Knowledge video

LAB Coming soon

Reverse engineering and app analysis
$100/month
  • 1 always-on box
  • 2 vCPU / 4 GB RAM / 25 GB disk
  • Analysis engines installed: nothing to licence, nothing to set up
  • Your phone over USB, and a live view of its traffic through the box
  • No Bot on this plan: the memory goes to the analysis engines instead
REAGhidraJADXapktoolmitmproxytsharkadbbinwalk
Watch the video Apply for the beta

Enterprise

Companies and resellers
Contact us
  • Dedicated hosts or a GPU slice
  • Private network and private AI endpoint
  • Service agreement and a named contact
  • Custom limits and invoicing
Contact us

Models in the paid plans

Paid plans add premium models from the Human.01 gateway, billed from your monthly AI credit. Free keeps Human.01 AI and the free models above.

Free

No credit. Human.01 AI and 19 free models from OpenCode, Kilo Code and OVHcloud.

Basic

Everything in Free, plus every premium model below from a small monthly credit allowance.

Pro+AI

The same models with more monthly credit and a priority queue, for heavier use.

Claude

Fable 5.1Fable 5Opus 5.5Opus 5Opus 4.8Sonnet 5.5Sonnet 5Haiku 5.5Haiku 4.5

GPT

GPT-6 AstraGPT-6.1 SolGPT-6 SolGPT-6 LunaGPT-5.6 SolGPT-5.6 TerraGPT-5.6 LunaGPT-5.4GPT-5.4 miniGPT-5.3 Codex Spark

Gemini

Gemini 3.1 ProGemini 3.8 FlashGemini 3.7 FlashGemini 3.6 FlashGemini 3.5 FlashGemini 2.5 ProGemini 2.5 FlashGemini 3.1 Flash Image

Human.01

Our own routed models: pick fast for quick answers or strong for hard problems.

Human.01 FastHuman.01 Strong

More than 50 models are in the gateway catalog, and the list changes over time. Premium models are billed from your AI credit at published per-token rates. AI credits launch during the beta.

Pay by crypto

Open your profile, pick a plan, and send the exact amount shown to our own deposit wallet from your wallet app. No payment provider in between. Longer plans cost less per month.

30 days90 days · about 10% off365 days · about 17% off

Phone bill Coming soon

Pay on your mobile carrier bill: no card, no code to type. Carrier billing is being set up with our first telecom partner.

Plans are in a private beta. The always-on boxes are available to beta members now; AI credits for premium gateway models and carrier billing arrive during the beta. Prices may change before the public launch.

Sixty minutes to build.
A day to decide.

Your box is free to use right away. When the hour is up it pauses; claim it with your email and it's yours to keep. Don't, and it disappears.

Now
60 min

Full access. Install, build and run whatever you like.

Then
24 hours

The box is paused. Open the claim link from your welcome message and confirm your email to keep everything exactly as you left it.

Otherwise
Deleted

Unclaimed boxes and their files are removed.

Free stays free
by being fair.

Boxes are generous but not unlimited. These rules keep the service open for everyone.

  • 3 new boxes per IP address per day. Reconnect with the same key as often as you like.
  • Web and git only. Outbound traffic is limited to HTTPS, HTTP, SSH, git and DNS. No mail, IRC or mining pools, and nothing can connect in.
  • No abuse. No spam, scanning, crypto mining or attacks. Keys and addresses that do are banned.
  • Busy sometimes. If every box is in use you'll see a short "try again" message. Failed attempts don't count against your daily limit.
  • Fair AI use. Each account gets 350,000 tokens of Human.01 AI per 5-hour session and 2,400,000 per week (about 10 million a month; Pro six times that), up to 30 requests a minute and 3 at a time per box, plus 6 images per hour and 20 per day. The free third-party models are shared and rate limited.
  • Bot replies. The free taste is 20 sent replies per box, at most 10 an hour.
  • IPv4 for now. Connect over IPv4; IPv6 is not supported yet.

Good to know.

Do I need an account?

No. Press Launch and this browser remembers your box, so coming back opens the same machine. Over SSH, your public key identifies it: the same key lands in the same box. To use one box from both, press "Use my own terminal" in the workspace.

What happens at 60 minutes?

The box pauses and your session ends. Your files are kept while it waits to be claimed. Connecting again shows how long is left to claim it.

How do I claim a box?

Your welcome message includes a claim link. Enter your email, confirm it from the message we send, and the box becomes yours, with your files intact. A claimed free box sleeps after 24 hours idle and is deleted after 7 idle days.

Is it a container or a virtual machine?

A virtual machine. Each box runs its own Linux kernel on a hardware-isolated hypervisor, so what happens inside stays inside.

Can I run a server?

Yes. Run your app on $PORT (8080) and open https://<boxid>.vm.human01.org - your box id and address are in the welcome message. Until you claim the box only your own connection can open it; once claimed it is public. Nothing else can connect in, and outbound traffic is limited to web and git.

Which AI models can I use, and do they cost anything?

No cost. The default is Human.01 AI (Qwen3.8 Flash Next 180B) on our own GPUs, plus 19 free models from OpenCode (DeepSeek V4.1 Flash, GLM-5.3-Flash and Beam, free for a limited time), Kilo Code and OVHcloud that you can switch to inside the agent. The free ones are shared and rate limited. Paid plans add premium Claude, GPT and Gemini models from a monthly AI credit.

How much AI do I get for free?

Every account gets 10,000,000 tokens a month of Human.01 AI (Qwen3.8 Flash Next 180B on our own A100 GPUs), metered the way Claude and Codex do it: a 5-hour session of 350,000 tokens and a rolling week of 2,400,000, each resetting on its own, with up to 30 requests a minute and 3 at a time per box. All your boxes share the two windows, and your first session after claiming is doubled. Pro accounts get 60,000,000 a month. The 19 free third-party models come on top and don't count against it. The AI usage panel in the workspace shows both bars, live.

What is the Bot, and is it safe?

The Bot is an assistant that answers your chat apps from its own screen in your box. It uses apps you sign in to there yourself, with their QR code. It writes drafts and you press Send: nothing is sent without you unless you switch automatic sending on. Payments, codes and private matters always wait for you, and its log shows everything it did.

How do I pay for a plan?

With crypto, straight to our own deposit wallet: open your profile, pick a plan, and send the exact amount shown from your wallet app. Or redeem a prepaid voucher: redeem it from your terminal and the plan starts. Carrier billing, where the charge appears on your phone bill, is coming soon. Plans are in private beta, so join the beta to get access.

How does image generation work?

Ask the agent for an image and it creates a PNG in your project with Qwen-Image. Each box gets 6 images an hour and 20 a day, and prompts are logged to catch abuse.

Which languages does it speak?

English, 简体中文, 繁體中文 and Bahasa Melayu. Pick one in the menu at the top of the page. The terminal, the claim email and the Bot follow it too.

Open a terminal.

Any terminal on Mac, Linux or Windows. No account, no credit card.

$ ssh vm.human01.org

Apply for the LAB beta

Tell us who you are and we will email you when there is a place.