SKKAN
FR
New · 4.1 “Seven seas” — a Launch council to scope a project (experimental), and an installer that refuses any unverified release →

SOKKAN Atelier · the AI assistant for the whole team

Ask for a piece of work. Approve it. Your team remembers.

You describe what you need, the assistant drafts it from your documents, and nothing is saved without your approval. Every answer says which model wrote it. What the team has decided stays in a shared memory, for next time.

Hosted in Switzerland or on your premises Full export, readable without SOKKAN Open source Apache-2.0
SOKKAN Atelier: on the left the request and the assistant’s answer with the deliverable card “Written by Claude Opus 5.5 · Anthropic”, on the right the document preview with the Validate the deliverable and Download as Word buttons

Real screenshots of SOKKAN Atelier (version 3.6.7, English interface) on a demo instance with fictitious data; the example texts were scripted for the capture.

SOKKAN Atelier · three steps

No commands to learn. Three steps.

The Atelier is made for teams whose work is documents: training, consulting, administration, communication. You start with a question, not with a tool.

1

Ask

Write what you want, as you would to a colleague, and attach your files (PDF, Word, PowerPoint, Excel). Or start from a template: training plan, summary, client proposal, quiz. You choose who writes: the model on the machine, or Claude when the project allows it.

The Atelier home screen: the request typed in, the choice between the machine’s model and “Write with Claude”, the warning that the request will go to Anthropic outside Switzerland and Europe, and four work templates
2

Approve

The assistant never files anything behind your back. Before saving a deliverable, it shows you a card: what it wants to save, the documents it read and how old they are. You read the draft, correct it if needed, then allow or refuse. Every approval is dated and logged.

The approval card: the agent wants to save “Module 4 — Running a remote session”, nothing is sent outside, with Allow, See the draft and Refuse buttons
3

Find it again

Everything approved is in My work, ready to download as Word. And when the team sets a rule (“our quizzes have ten questions at most”), it goes into the project memory: the assistant rereads it for every new piece of work, for everyone. The more you work, the less you repeat yourself.

The Memory page: “What SOKKAN retains for this project. The agents read these notes again for every piece of work.” with two notes, the standard format of introduction workshops and the tone of the course materials

Transparency

You always know who wrote it.

Every answer and every deliverable carries a label: the model that wrote it, and where it runs. The administrator decides which projects may use Claude; confidential projects stay on the machine’s model, no exceptions.

A deliverable labelled “Written by Claude Opus 5.5 · Anthropic” and the assistant’s answer listing the points to confirm
Written by Claude: the label says so, on the answer and on the deliverable.
A deliverable labelled “Written by Local model · on your machine”, with the green label
Written on the machine: “Local model · on your machine”, nothing left the building.

Two interfaces, one memory

Each their own screen. The same knowledge.

Not everyone in a company does the same job. With SOKKAN, one company account holds both: each person picks their interface, and everyone works on the same memory and the same inference.

For teams

SOKKAN Atelier

For people who want a result, not a tool.

  • Ask for a piece of work, in English or in French
  • Approve a card before anything is saved
  • Every answer says which model wrote it
  • Deliverables download as Word
SOKKAN Atelier: the home screen, a request and the choice of the model that writes
For technical people

SOKKAN Cockpit

For people who run agents every day.

  • Agent sessions in parallel, from a kanban board
  • Agents that run on their own, one card per agent
  • Full transcripts, every tool call
  • Costs, audit log, deployments, fleet
The Cockpit, Crew tab: agent cards in Idle and Armed columns, each with its schedule, model, last run and cost
One memoryWhat the team decided, reread by every piece of work, in both interfaces.
One inferenceThe same models and the same per-project rules, in both interfaces.
One accountThe same people, roles and projects, whichever interface they use.

SOKKAN Atelier is in beta in SOKKAN 3.6: it is switched on per instance. Both can be visited read-only, no account needed: the Atelier and the Cockpit, on fictional work already done.

Your data

With us in Switzerland, or on your premises. And you can take everything with you.

Or on your premises

On your own server, or in a box delivered ready to plug in. With the machine’s model, nothing leaves your premises: not the documents, not the memory.

Install SOKKAN →

Take everything with you

One button, a single zip file: the memory notes, the agents and the deliverables, readable without SOKKAN. No secret is included.

Settings, “Our work” section: a single zip readable without SOKKAN, the “Export our work (.zip)” button and the “Archive downloaded” confirmation

SOKKAN Cloud · pricing

Operated for you, in Switzerland.

The same SOKKAN, minus the ops: a dedicated VM in the Geneva zone, your own private network, your URL at you.sokkan.ch. Bring your Anthropic key or take managed inference, served from our own GPUs in Geneva (fallback in France, or a 100% Swiss tier), prepaid credits from CHF 25 (+25% credits from CHF 500), metered per token. Free 14-day trial on every plan: card required, first charge on day 14, cancel in one click before (trial seats are limited).

Starter

CHF 129 · €129
per month · cancel monthly
  • Dedicated VM 2 vCPU · 4 GB · 50 GB NVMe
  • Solo: 1–3 parallel sessions
  • Your URL you.sokkan.ch + private network
  • Unlimited project memory, on your VM
  • Your key or managed inference (credits)
  • Updates & monitoring by NINABOT
Get started

Standard · recommended

CHF 249 · €249
per month · cancel monthly
  • Dedicated VM 4 vCPU · 8 GB · 100 GB NVMe
  • 1–2 users: ~5 parallel sessions
  • Your URL, private network, growable fleet
  • Workers & managed Postgres in two clicks
  • Team roles (viewer/dev/admin) + audit log
  • Root maintenance terminal (audited)
Get started

Studio

CHF 490 · €490
per month · cancel monthly
  • Dedicated VM 4 vCPU · 16 GB · 200 GB NVMe
  • Agency: multi-project, dense sessions
  • Everything in Standard, bigger
  • Inference usage broken down per user
  • Prorated plan changes, self-service
  • Priority email support
Get started

Grow from the cockpit: worker instances from CHF 59/mo · managed PostgreSQL from CHF 99/mo (daily backups), inside your private network. Web exposure included: HTTPS subdomains and your own domains, automatic certificates, at no charge. Prorated billing, provisioning after payment, cancel monthly.
Hosted at Exoscale (Geneva), operated by Ninabot Sàrl: your data stays in Switzerland. Not sure about sizing? [email protected], you’ll get the founder, not a bot.
In the press: ICTjournal, “Ninabot launches a Geneva-hosted cloud for AI agents” (in French, 04.08.2026).

Book a 30-min demoSee the live Cockpit, no account

For technical teams

Open source, installed in one command.

SOKKAN is released under the Apache-2.0 licence: the same product, the same repository, whether you host it or we operate it. The managed cloud pays for operations, not for crippled features.

The Cockpit is an agentic studio: a kanban board where every card becomes an agent session, human sign-off on every action that changes something, scheduled agents, a secrets vault, per-session costs and an audit log. The code on GitHub →

Free, no limits

On your machine, in one command.

Docker, plus your Anthropic key or your Claude Pro/Max subscription. Everything stays on your machine.

$curl -fsSL https://sokkan.ch/install.sh | sh Requirements: Linux (or macOS with Docker Desktop), about 4 GB of RAM. No Docker? The script offers to install it (official get.docker.com script).
Sources: tarball · script, read it before piping to sh, obviously.

The helm, not the autopilot

Agents’ permission requests and questions become buttons. Nothing irreversible without your click, nothing marked done without you.

Alert → diagnosis session

A production alert opens a session that knows the project, proposes a fix and waits for your green light, with a Telegram ping to come and give it.

Agentic observability

Metrics and logs inside your network; your sessions read them and compose a dashboard on request.

Secrets vault

Encrypted and injected into sessions as environment variables: the agent uses them without the value ever showing, on screen or to the model.

Replayable runbooks

A procedure is a memory note. “Replay” opens a guided session, step by step, with human sign-off on anything irreversible.

Deploy, roll back

Deploy an image to a worker in your fleet, roll back to the previous version in one click. Per-session costs, an audit log of every action.

Memory, measured

82%

of questions get the right note as the first result with SOKKAN 3.0’s memory on a GPU, against 42% with 2.x. Without a GPU, on a small server: 73%. The memory reviews itself (CortHeXis tab) and proposes its fixes, which wait for your approval.

SOKKAN 2.x42% · MRR 0.55
SOKKAN 3.0, no GPU73% · MRR 0.82
SOKKAN 3.0, GPU or ANCHOR82% · MRR 0.88

Benchmark of 300 questions in French, English and German, asked of our own working memory (415 notes), 2–3 October 2026. “First result”: the expected note comes out on top; MRR: mean reciprocal rank (1 = always on top). Memory in detail, method and profiles · CortHeXis, the open-source engine.