Context, references, success criteria and order live on the board, not in your chat history. Your agent reads them at the start of every session. Add another agent and it reads the same board.
New Agents connect over MCP →Works with Claude Code, Cursor, and any MCP client.
An app for splitting group trip expenses. Friends add what they paid, everyone sees who owes whom, settling up takes one tap.
3The payoff screen. Fewest possible payments to make everyone whole.
Share a link, friend lands in the trip. No account needed to view.
Trips abroad log expenses in local currency, settle in home currency.
Snap the receipt, attach it to the expense, keep the original.
Turns all expenses into one clear answer: who owes whom.
Email plus password sign-in with a 30-day remember-me option.
A trip holds people and expenses. Name, dates, and a cover color.
The context an agent would otherwise guess at lives on the card: references, screenshots, tone, edge cases, and what it depends on.
Mentat runs no model of its own. Connect the agent you already pay for and it works directly against your boards.
Success criteria are yours to write and yours to tick. Neither the agent nor Mentat can mark a piece of work complete.
Description, reference links, screenshots, files, and notes on tone and edge cases. Everything the agent would otherwise have to guess sits on the card, and board-level context flows down to every card underneath.
After a trip, everyone opens this once. It has to answer "what do I owe, and to whom" in under three seconds, with no mental math.
Plain and calm. Never "Oops!" or exclamation marks. Amounts always show the currency symbol and two decimals.
splitwise.com settle-up flow
A checklist in your words, attached to the card. The agent builds against it. Nothing marks itself complete, and the card cannot pass review until you tick the boxes yourself.
Go ahead, tick them. On this page and in the product, that is a decision only a person makes.That is the whole idea. The agent could not have done that part.
Mentat speaks MCP. Paste one command and your agent can pull briefs, create cards, and advance its own work. No agent of ours, no inference bill, no lock in. Or export any card as clean Markdown and paste it anywhere.
Size the work and set your real working hours once. Mentat forecasts when each piece arrives and respects the order you declared, so dependent work never gets scheduled first.
Mentat is planned in Mentat and built by an agent against criteria a human ticked. Newest first.
No. There is no model inside and no inference cost. Mentat structures the work so the agent you already use can execute it.
Those track work for teams of people. Mentat is built for briefing an agent: every card carries the context, criteria, and ordering an agent needs to act without asking.
Any MCP client, including Claude Code and Cursor. You can also export any card or column as Markdown and paste it into anything.
No. You describe what you want and check the result against criteria you set. The agent writes the code.
Free while in beta, no credit card. Your first brief takes about two minutes.