LedgerPilot: a private cashflow copilot for the one-person business

Description and use

LedgerPilot gives freelancers a five‑minute cash‑flow review, generating summaries, projections, and actionable plans from a CSV export, with optional local LLM inference.

Problem

Freelancers and one‑person businesses need a quick way to assess monthly cash health, runway, and next actions without a full accounting dashboard.

Outcome

LedgerPilot enables a one‑person business to perform a five‑minute monthly cash‑flow review, reducing uncertainty and avoiding unpredictable API costs.

Workflow

• Upload a CSV with columns date,description,amount,category
• Server parses CSV and calculates income, expenses, category totals, monthly net cashflow, average monthly change, volatility, and runway
• Deterministic forecast generates a six‑month projection
• If Ollama is configured, the server sends the structured summary to the qwen2.5:3b model to produce a headline, three actions, and one watchout; otherwise a deterministic fallback is used
• Frontend displays the summary, forecast, and action plan
• User reviews the results and decides next steps

Evidence

LedgerPilot is a small cashflow copilot for freelancers and one-person businesses.

Source

It takes a CSV export from a bank, Stripe, PayPal, or accounting tool and turns it into: a clear income, expense, and net-cashflow summary – category-level spending signals – a six-month expected and cautious-case projection – three specific actions, written in plain language

Source

The server parses the CSV and calculates the facts: income, expenses, category totals, monthly net cashflow, average monthly change, volatility, and runway.

Source

If OLLAMA_URL is configured, LedgerPilot uses Ollama and the qwen2.5:3b model by default.

Source

The app has no database and does not require a bank connection.

Source