Objectives and key results
Outcomes with numbers on them, checked in over time.
One connector · 75 tools
Your assistant runs the whole plan. Not just the tickets.
Objectives, key results, epics, docs and releases — all reachable over one authenticated connector. The board is where your team looks at what the assistant already did.
30 days free, no card. No AI credits, ever.
What that looks like
Things you can ask on day one. Every one of these maps to tools that exist.
- Turn this call into an epic with acceptance criteria, under the retention objective.
- What is blocked right now, and who is waiting on me?
- Draft the release notes for everything that shipped this week.
- File that as a bug, link it to the objective it threatens, and tell me what it delays.
There are no AI credits
Most tools meter the AI: an allowance per seat, credits you buy, an agent that stops when the balance runs out. That is because they pay for the model behind it.
Here the model is yours. Your assistant connects with your own subscription, so a tool call costs us a database query and costs you nothing. Use it all day. There is no meter, and there is no plan on which one appears.
What the assistant can reach
The planning layer, not only the ticket layer — which is the difference between an assistant that files work and one that runs a cycle.
Epics and work items
Tasks, bugs, chores and feedback, with legal status transitions.
Docs with revisions
Specs, decisions and runbooks — written and diffed by the assistant.
Releases and notes
What shipped, assembled from the work rather than typed again.
Feedback ingest
Reports arrive from a widget or SDK and become triaged work.
Search across everything
One query over objectives, work, docs and releases.
Pricing
One price for the team, not per seat per month forever.
Starter
€19/month
One small team, getting the habit.
Team
€49/month
The whole team, all the projects.
Business
€149/month
Everything, plus what ships next.
Made by one person
No investors, no sales team, and no logo wall — you would notice, so it may as well be said first. What that buys you: the person who builds it answers your email, a feature request can ship the same week, and the price is not funding a growth target.
What it costs you: fewer integrations than the incumbents, and a bet on something small. Self-hosting is supported precisely so that bet is reversible.
Questions
Which assistants does it work with?
Any client that speaks MCP. Claude Code and the Claude apps connect over an authenticated connector; anything else that implements the protocol works the same way. There is a read-only endpoint too, for a key you would rather could not change anything.
Do I have to pay for AI usage on top?
No, and there is nothing to top up. The assistant is your own subscription — we never call a model and never bill you for one. The price is for the workspace.
What happens when the free month ends?
The workspace becomes read-only. Nothing is deleted and you are not locked out; everything is still there and still readable until you decide.
Can people who do not use an assistant still use it?
Yes. The board, docs and objectives are an ordinary web app. The connector is how the work gets in quickly, not the only way in.
Where does the data live, and can I host it myself?
On EU infrastructure. Self-hosting is supported — it is the same container the hosted version runs, on Postgres you control.
Is my data used to train anything?
No. Your content is not used for training and is not sold. The assistant that reads it is the one you connected.