finicast
Sign inGet started

The modeling database for AI agents.

Tables, pivots and conditional formulas that recalculate instantly.

Tell your agent:
Read https://finicast.com/agent and build my model in FiniDB

Or let it install the engine itself: npx finidb guide

Works with Claude Code, Codex, Cursor and any MCP client.

Create a projectRun locally npx finidb serve
A P&L pivot with a formula bar; editing growth updates the forecast
A P&L pivot table (a grid of line items × periods with formulas placed by condition). Editing growth recomputes every forecast cell.

Spreadsheet vs FiniDB

Spreadsheets were designed for eyes and mice. FiniDB was designed for agents: named tables, named line items, named periods, formulas placed by condition — no cell addresses, no copy-down, no broken ranges.

A spreadsheet with the same SUMIFS formula copied across hundreds of cells
=SUMIFS($C:$C,$A:$A,$A2,$B:$B,B$1) copied across 720 cells.
FiniDB method
frame = hist: SUM(SELECT("amount","ledger","account","=",THIS("account"),"period","=",THIS("period")))

Add rows to ledger, add accounts, add periods: nothing to recopy. The method applies to every cell whose frame is hist.

One formula, placed by condition.

A worked example: an income statement

Two historical years and three forecast years. Eight line items, eight formulas. History and forecast carry different formulas for the same line, because the condition places them — that is the whole idea.

Line itemHistorical years frame = histForecast years frame = fcst
Revenue revenueentered from the actuals'prior revenue' * (1 + 'growth')
Revenue growth growthIFERROR('revenue' / 'prior revenue' - 1, "")entered: the driver you tune
COGS cogsentered from the actuals'revenue' * LOOKUP("value","drivers","id","cogs_pct")
Gross profit gp'revenue' - 'cogs''revenue' - 'cogs'
Gross margin gm'gp' / 'revenue''gp' / 'revenue'
Opex opexentered from the actuals'prior opex' * (1 + LOOKUP("value","drivers","id","opex_growth"))
Operating income opinc'gp' - 'opex''gp' - 'opex'
Operating margin opm'opinc' / 'revenue''opinc' / 'revenue'

Read one row: revenue growth is derived in history and assumed in the forecast, and the same line carries both formulas because each one names the years it applies to. 'prior revenue' is the previous period of the revenue line; frame comes from a Frame column on the periods table, so adding a year changes nothing else.

 2024hist2025hist2026fcst2027fcst2028fcst
Revenue1,0001,2001,4161,6281,824
Revenue growth—20.0%18.0%15.0%12.0%
COGS420480538619693
Gross profit5807208781,0101,131
Gross margin58.0%60.0%62.0%62.0%62.0%
Opex380430473520572
Operating income200290405489558
Operating margin20.0%24.2%28.6%30.0%30.6%
What the model computes. Change the 2026 growth to 30% and revenue becomes 1,560, carrying through 2027 and 2028 and every margin below.
Build it
curl -O https://finicast.com/income-statement.json
npx finidb apply income-statement.json --data ./model
npx finidb query ./model is

One file: the periods with their Frame, the line items, the drivers, the entered actuals, and the eight methods above. Read it — it is the whole model, and it is what an agent writes.

Why an agent is better off in FiniDB

Eight claims, each demonstrable in the model above. Numbers are engine-time benchmark targets from the FiniDB benchmark suite.

  1. 01

    No coordinates

    A1:F1 becomes revenue for frame = fcst. The agent never reasons about where a value lives.

    account = rev AND frame = fcst
  2. 02

    One formula per concept, not per cell

    A P&L with 200 accounts × 60 periods is ~20 formulas, each attached to a condition. Fewer tokens, reviewable diffs.

    frame = fcst AND account = rev:
PREV("value") * (1 + growth)
  3. 03

    Facts stay in tables

    100,000 ledger rows are a table with an index, not 100,000 rows of a sheet. SUM(SELECT(...)) replaces SUMIFS over ranges that break when rows are added.

    SUM(SELECT("amount","ledger",
  "account","=",THIS("account")))
  4. 04

    Time is a dimension

    Periods live in a table with Frame (hist/fcst), quarters, years. PREV, CUMULATIVE and YTD work by name.

    PREV("value")   CUMULATIVE("rev", -2)   YTD("rev")
  5. 05

    Instant, incremental recalculation

    A changed input recomputes only its dependents, even with 100,000-row fact tables.

    100,000 rows, 1 change, < 1 ms engine time (B1.2 target ≤ 5 ms) benchmark

  6. 06

    Explainable

    Any cell can say which formula produced it and which inputs fed it. Agents verify their own work.

    POST …/tables/pl/cells/explain
  7. 07

    Deliverable to humans

    The same model renders as a modern grid UI and exports to Excel (values + formats) for stakeholders who want a workbook.

    finidb export ./model xlsx --out model.xlsx
  8. 08

    A real database

    Users, passwords, many databases per server, REST API, MCP server, CLI. Locally with npx finidb or hosted at finicast.com.

    finidb://user:password@host:7407/database

How an agent uses it

Five steps, each one MCP tool or one REST call against the same API.

  1. 1

    Connect

    MCP
    finidb_describe
    REST
    GET /db/<project>/models
  2. 2

    Describe the data

    MCP
    finidb_import_csv
    REST
    POST /db/<project>/import/csv
  3. 3

    Create tables & pivots

    MCP
    finidb_create_table · finidb_create_pivot
    REST
    POST /db/<project>/commands
  4. 4

    Place formulas

    MCP
    finidb_add_method
    REST
    POST …/tables/pl/methods
  5. 5

    Verify & export

    MCP
    finidb_list_errors · finidb_export
    REST
    GET …/export/xlsx

Live demo

A read-only sales-ops model: edit the growth input and watch the pivot update, with a timing badge showing engine time.

Static render of the demo P&L pivot
Interactive demo arrives with the workspace; until then this is a static render.

Runs anywhere

Embedded with no daemon, a local daemon, or hosted here. Same commands, same file format.

npm

npm install -g finidb
finidb serve --data ~/finidb-data --port 7407

Docker (planned)

docker run -p 7407:7407 -v finidb:/data ghcr.io/finicast/finidb serve

Hosted

One project = one database with its own user and token, behind finicast.com.

Create a project

For humans too

The same model renders in a workspace: grid, pivot builder, conditional formulas, explain panel, export to Excel. Free while in preview.

  • Grid

    Virtualised tables and pivots with frozen headers and frames.

  • Pivot builder

    Drag reference tables into rows, columns and cells.

  • Conditional formulas

    Name, apply on, where-chips, formula. Last match wins.

  • Explain panel

    Which method produced this cell and which inputs fed it.

  • Export to Excel

    Values and formats, one sheet per table or view.