Skip to content
OpenLedger

A reliable, deterministic ledger for your AI.

OpenLedger is the harness that keeps your AI from hallucinating your money: it turns scattered bank and credit-card statements into the source of truth behind any financial app it can build.

npm install -g @aquartier/openledger

Then paste one line into your AI. Two steps, about a minute.

Works with the AI you already use

  • ChatGPT
  • Claude
  • Gemini
  • Claude Code
  • Codex
  • Cursor
  • OpenCode
  • PIPI
  • OpenClaw

Why OpenLedger

Apps never fit, and raw AI failed you too

Every finance app is someone else’s idea of your money: someone else’s categories, someone else’s dashboard, someone else’s idea of a good month. The one that fits you is the one you build.

A deterministic place for every number

Your AI reads the statements you already receive and records what it finds as double-entry bookkeeping. Every number lives in your ledger, not in a model’s memory.

Private by default

Everything stays on your machine in a local SQLite database. PII is redacted before anything reaches an AI provider. No bank logins, no cloud aggregator, no telemetry.

What your AI builds

Every app below is a prompt away. One ledger underneath, so the numbers agree across all of them.

Spending Tracker

Prompt:

“Install OpenLedger and set up my ledger from my statements. Then build me a spending tracker that sorts every dollar into envelopes.”

A private YNAB that already knows where your money goes.

Personal CFO

Prompt:

“Install OpenLedger and set up my ledger from my statements. Then be my CFO: review my month and tell me what to fix.”

An advisor that knows you best and tells no one.

Budget Planner

Prompt:

“Install OpenLedger and set up my ledger from my statements. Then build me a budget planner that charts my what-ifs.”

See your money in ways no app ever shipped.

And your own.

Describe it. It ships tonight.

Whatever you imagine, running on numbers that balance.

How it works

  1. Give your AI a ledger

    One command, one skill file. Your AI gets a deterministic home for every number. No more making them up.

  2. Hand it your statements

    Drop in the PDFs your bank sends every month. Each line becomes double-entry bookkeeping, and anything unclear becomes a question, not a guess.

    “Ingest my new statements.”

  3. Vibe-code your dream finance app

    A budget planner, a spending tracker, a subscription auditor, a retirement planner. Any app you imagine, on numbers that add up.

    “Build me a money coach that knows my spending.”

Install

AI apps

ChatGPT · Claude · Gemini

  1. Install the CLI

    npm install -g @aquartier/openledger

    Installs the oled command.

  2. Paste into your AI chat

    Fetch https://cdn.jsdelivr.net/npm/@aquartier/openledger/skills/SKILL.md
and follow it. oled is installed; help me set up my ledger.

    If your app can’t fetch URLs, oled setup --print | pbcopy copies the skill itself. Drop it into the first message.

Coding agents

Claude Code · Codex · Cursor · OpenCode · PI · OpenClaw

  1. Install the CLI

    npm install -g @aquartier/openledger

    Installs the oled command.

  2. Add the skill

    npx skills add phureewat29/openledger

    Or run oled setup. It writes the skill to .agents/skills/, the shared directory most agents read. Pass --dir <path>, e.g. --dir .claude/skills for Claude Code.

Under the hood

The model reads your statements; the ledger checks the math. Every posting balances, or it doesn’t post.

  • Double-entry ledger

    Every transaction debits one account and credits another, so the same input always produces the same books.

  • Local SQLite

    One file in ~/.oled with 0600 permissions. Your machine is the database.

  • PII redaction

    Names, account numbers, and free text are masked before anything goes to your AI provider. The ledger file itself never leaves.

  • Reference datasets

    Built-in institution data for the US, Japan, Thailand, and China, so your AI recognizes the bank behind every statement.

  • Questions, not guesses

    When a line is ambiguous, OpenLedger surfaces it for you to resolve instead of letting the model pick.

100%

of your ledger stays in one local file

Zero

bank logins or credentials

9B

smallest model benchmarked

2B

smallest OCR benchmarked

Benchmarked with small models

The harness carries the bookkeeping, so the model doesn’t have to be huge. Small, even local, models run the same statement through the same checks, and the books come out identical.

google/gemini-3.6-flash · 126-row card statement

PASS

  • Statement rows posted

    126 of 126

  • Charge rows matched

    120 of 120

  • Refund rows matched

    5 of 5

  • Card payment rows matched

    1 of 1

  • Uncategorized rows

    0 of 126

  • Truthful claims

    3 of 3

Statements read through Typhoon OCR 1.5 2B.