sokkosai
Sign in Start free
four packages · free hosted · €29 with help · €49 install · custom from €99

Free. €29. €49. Custom.

Same agent under the hood. Hosted Auto is free — come spend as long as you like, see how agents work, decide if you want my help. It runs on your own free Google Gemini key and sleeps when idle. No platform run limits.

⚒
Set up & run for you
I do the wiring — model, Telegram, your first automations — and keep it running. You skip the fiddly part.
⊞
Hosted in the EU
Your agent runs on a VPS in the EU (Hetzner, Germany/Finland). The AI model is your choice, on your own key — processed under the terms of that provider; we never resell your data or train on it.
⌶
On your own free Google key
Free Gemini is the default — you paste your own key, so the quota stays yours and we never bill per run.
✉
A human answers
A real person (Konstantin), not a vendor bot. Written replies within 24h on the paid tiers. Export everything, no lock-in.
Free · sleeps when idle
hosted auto · hosted auto
Hosted Auto
Free
→ Free forever. Drop in your Telegram token + your own free Gemini key, and your agent runs itself. You do everything yourself — after 3 quiet days it goes to sleep (we warn you a day before), and one click in your dashboard wakes it.
  • ·Your own OpenClaw agent, hosted on our server — live in minutes
  • ·Default model: your own Google Gemini free key — no bill from us
  • ·Watch sites, summarise news, set crons — by chat or voice
  • ·Built-in helper fixes the agent on request; web terminal for the curious
  • ·Sleeps after 3 quiet days to save resources — wake it with one click in your dashboard
  • ·Export everything anytime — no lock-in
Bot/FAQ + the agent's built-in self-fix
Start free
★ most popular
hosted plus · hosted+
Hosted+
€ 29 /mo hosting
→ Everything in Hosted Auto — plus at order time you tell us which models, API keys, messengers and crons you want. The agent sets them up, or I do it by hand.
  • ·Everything in Hosted Auto, plus setup help
  • ·Tell us the models / keys / messengers / crons — agent or I wire them up
  • ·Custom skills the agent can't learn on its own — I write them
  • ·Extended assistance: the agent configures, I step in when needed
Agent (extended) + me, by hand
Get Hosted+ at €29/mo
min install · minimal install
Minimal install
€ 49 one-off
→ I install it for you — on our hardware or yours. The €49 one-off includes the install + 7 days of written support. At order time we ask whether you want ongoing support after that.
  • ·Remote session: web terminal or RustDesk — your pick
  • ·Full OpenClaw + your keys wired (Gemini / OpenAI / Claude / …)
  • ·Telegram or Slack bot connected
  • ·2-3 starter automations + a short guide
  • ·7-day written support included
  • ·Optional: add Light maintenance at €9/mo
Install + 7 days of written support included · optional €9/mo Light maintenance (maint-light) after
Order €49 — pay & start

One-off — fine to order alongside any hosting plan.

custom · custom
Custom
from€ 99 one-off
→ Anything irregular — Gmail with OAuth, managing your websites, complex integrations. You send a brief, I quote, work starts after payment.
  • ·Gmail / Google OAuth integrations
  • ·Website management & automation
  • ·Complex multi-service integrations
  • ·Brief → quote within 24h → work starts after payment (no upfront free work)
Optional ongoing support from €29/mo (maint-full), scope-dependent
Brief me — quote in 24h

Brief → quote within 24h → work starts after payment. No upfront free work.

your own server · one-off setup + monthly server

Dedicated VPS. A whole machine, just yours.

→ A whole server we run for you alone — not a shared container. €99 one-off setup (handled as a Custom project), then only the monthly cost of the server itself — sized to your needs and passed through at provider cost.

  • ·Your own isolated VPS — not a shared container
  • ·€99 one-off setup — same as a Custom project
  • ·Then only the monthly server cost, sized to you (passed through at cost)
  • ·Brief me → I size the server → quote → provision
  • ·Tracked + managed from your dashboard like a hosted agent
Get a quote

Optional Full maintenance from €29/mo (maint-full)

custom project · from €99 · brief → quote → pay → work

Tell me what you need. Quote in 24h.

Fill in the brief below. I'll reply within 24h with a fixed-price quote. Work starts after payment — no upfront free work, no vague estimates.

No payment here. You'll receive a fixed-price quote by email within 24h. Work starts only after you pay.

your keys · your bill

Bring your own model keys. All of them right in the dashboard.

Default is Google Gemini 3.1 Flash Lite (500 req/day · 15 req/min · 200K ctx, free) — paste that key right in the dashboard. Want ChatGPT, Claude, OpenRouter, Groq, NVIDIA, DeepSeek, or any OpenAI-compatible endpoint? Add them right in the dashboard under Get started — no terminal needed. The bill stays with you.

Google Gemini
default · free · via dashboard
Free API tier from aistudio.google.com — paste your key right in the dashboard. Default model: Gemini 3.1 Flash Lite. 500 req/day, 15 req/min, 200K effective context per call.
quota · 500/day · 15 req/min · 200K ctx
OpenAI · API key
via dashboard · paid
API key from platform.openai.com — separate billing from ChatGPT Plus. (ChatGPT Plus is the chat app; it does NOT include API credits.) Add it right in the dashboard under Get started.
quota · pay-per-token · your bill
Anthropic Claude · API key
via dashboard · paid
API key from console.anthropic.com. Note: Claude.ai (the chat) is separate — that subscription does NOT give you API access either. Add it right in the dashboard under Get started.
quota · pay-per-token · your bill
10+ providers — Groq, OpenRouter, NVIDIA, DeepSeek…
via dashboard · free & paid
Groq Compound (free), OpenRouter :free models (free), NVIDIA NIM (free credits), Z.AI GLM (free), Moonshot Kimi (free), xAI Grok, DeepSeek — all configurable in the dashboard. Free-tier options marked in the provider dropdown.
quota · provider-dependent
Custom · OpenAI-compatible
via dashboard
Any endpoint that speaks the OpenAI HTTP API — Azure OpenAI, Ollama, vLLM, your own server. Enter the base URL, key, and model id in the dashboard under Get started.
quota · depends
≡
What we don't sell.
No run quotas.
Run your agent as much as you want. The only ceiling is your Google / model-provider quota. Linked from your dashboard, owned by you.
No "skill slots".
The agent learns whatever you ask. "Add a cron" works. "Add another cron" works. There is no quota and never will be.
No lock-in.
Export everything in one click. Move it to your own server. We'll even point you at the docker-compose to run it yourself.
No "2-agent" upsell.
It is one agent. It spawns sub-agents internally when it needs to. No artificial quota on that either.
ChatGPT Plus is not an API key.
The €20/mo ChatGPT subscription is for the chat app. To use OpenAI from inside your agent you need a separate API key (pay-per-token). Same for Claude.ai. We will explain in plain language.
No free trial.
Cancel in 14 days for a full refund instead. Cleaner than a trial that "auto-converts".
No annual lock-in.
Monthly. Cancel any time. I will add annual only when many people ask.
add-ons · stack onto a package · not a standalone tier
Light maintenance
I watch the heartbeat and restart on crash. — available for: manual, hosted-auto, hosted-plus packages.
€ 9 /mo
Full maintenance
Light maintenance + tweaks + new skills when you ask. — available for: custom, dedicated-vps packages.
€ 29 /mo

These are optional recurring add-ons — not standalone hosting tiers. The €29/mo Full maintenance add-on attaches to a Custom project; the €29/mo Hosted+ tier above is a monthly hosting subscription. Same price, different things.

honest answers
"Are there really no run limits?"
Yes, really. No platform-side run limits. The cap is your model provider's. Default is Gemini 3.1 Flash Lite — 500 requests/day, 15 requests/min, 200K context per call, free from Google with no card. When you hit it, the agent waits or routes to your paid key (Claude/OpenAI/custom) if you've added one.
"What does Assisted actually buy me?"
My time, asynchronously. You say "I want X". I reply in 24h with either a working setup, an explanation, or a question. If the agent cannot learn something alone, I write the custom script. Same async rules — no calls.
"What does 'manual setup' involve?"
€49 one-off. I install the full OpenClaw agent on your hardware (Mac, Linux PC, VPS, or spare laptop). We pick the models together (Gemini free / OpenAI / Claude — your keys), wire a Telegram or Slack bot, and set 2-3 starter automations. You get 7 days of written support via the Telegram support bot — anything breaks in week 1, I fix it. After 7 days you can move to Assisted (€29/mo on my VPS) or keep maintaining it yourself with the PDF guide. Prefer to try first? Hosted Auto is free.
"Can I leave?"
One click in dashboard → full tarball: agent config, history, embeddings, every cron, every script. Inside is a docker-compose.yml. Run it anywhere. We hate lock-in more than you do.
"Can I use my own ChatGPT / Claude subscription?"
Almost. ChatGPT Plus and Claude.ai are chat apps — they don't include API access. To plug into the agent you need an API key: platform.openai.com/api-keys or console.anthropic.com. Those are pay-per-token, separate billing from any subscription you might already have. We're not in the middle of it.
"Can I just SSH in and edit things myself?"
Yes. There's a web terminal in dashboard. Add cron jobs, install packages, peek at logs. If you break it on free Hosted Auto, restoring is on you — that's the deal. On Assisted (€29), I'll un-break it.
💬 Need help? Chat with us on Telegram