Full site context for agents: https://tansohq.com/llms.txt

Credit Estimator

"When do I run out?" Answered in your own dashboard.

Embeddable, provider-neutral credit forecasting. Burndown runway for sellers, pre-commit planning for buyers, from data your app already has. Six npm packages, MIT licensed, works with or without Tanso.

Two questions, one core

Forecast, for sellers. When does this customer run out? Feed it observed daily usage and a balance. The deterministic core projects the ending balance, depletion risk, and shortfall across explicit low, base, and high scenarios, and the React package renders it inside your dashboard.
Plan, for buyers. How many credits should I buy? No history needed. Per-metric usage estimates times credit weights, scaled across scenarios and compared against a candidate allocation. Everything is an explicit input. It never invents weights, prices, or predictions.

Packages

Install the two most people start with:

npm install @tansohq/credit-forecast-core @tansohq/credit-burndown-react

@tansohq/credit-forecast-schema. Provider-neutral Zod schemas and TypeScript contracts.
@tansohq/credit-forecast-core. Deterministic burndown and planning calculations, browser and Node.js.
@tansohq/credit-burndown-react. Controlled, accessible React components.
@tansohq/credit-forecast-json. Deterministic JSON import and export.
@tansohq/credit-forecast-csv. Portable multi-file CSV import and export.
@tansohq/credit-forecast-tanso. Optional Tanso snapshot-to-neutral mapping.

Design constraints

The core reads no clock, network, or product state; inputs are explicit and results carry full calculation traces. It is read-only by design. It never owns wallets, ledgers, or payments, and it never writes back to your billing system. An optional adapter maps a Tanso snapshot into the same neutral input any other host supplies.

Links

More for agents: https://tansohq.com/llms.txt