Skip to main content

Bean Labs

Researching the boundaries of autonomous financial intelligence.

A research initiative by Beancount.io

Bean Labs publishes open research notes on autonomous bookkeeping — language models that reason over double-entry ledgers, produce verifiable audit trails, and stay grounded in plain-text accounting.

Research by topic

Browse the research log by the themes we return to most often.

LLM

Large language model research with applications in financial tasks

More on LLM

AI

Artificial intelligence research and applications in finance and accounting

More on AI

Machine Learning

Machine learning techniques for financial data analysis and automation

More on Machine Learning

Beancount

Beancount ledger format, tooling, and ecosystem research

More on Beancount

Automation

Automation techniques and tools for financial data processing workflows

More on Automation

Data Science

Data science methods applied to financial datasets and accounting workflows

More on Data Science

Finance

Financial research, analysis, and domain knowledge for accounting AI

More on Finance

Plain-Text Accounting

Research grounded in plain-text accounting formats and workflows

More on Plain-Text Accounting

How we approach research

Plain-text first

Start with plain-text ledgers so the inputs remain readable, portable, and open to inspection.

Reproducible by default

Make the inputs, methods, and limitations explicit so others can examine and build on the work.

Open findings

Publish research notes openly and invite the community to question, extend, and improve the findings.

Follow the research

Read the published notes and follow the next questions in the research log.