Projects

Ladle — Open-Source Prep Forecasting and Food-Cost Leak Detection

Active
Python 3.11-3.13FastAPINext.js 15CLICSV / Square / Toast adaptersApache-2.0
Product demo

Problem

Restaurants throw away 4-10% of the food they buy before it reaches a plate, and most owners find out at month end from a food-cost percentage that moved the wrong way, with no idea which ingredient did it. The tools that solve this sit behind a per-location subscription, a sales call, and your data on someone else's servers.

Business Impact

Nory, Winnow, Leanpath, MarketMan, and Tenzo solve this problem for restaurants that can afford a per-location subscription. Ladle is the open-source alternative for the ones that cannot — the same three morning answers, self-hosted, with the data staying on the operator's own machine.

System Approach

  • Four-step core loop: ingest sales, forecast demand, explode recipes, compare theoretical versus actual
  • Per-item demand forecast with a safety margin drives the prep sheet
  • Purchase order computed as forecast times recipes minus stock on hand
  • Leak board prices theoretical-versus-actual usage variance per ingredient
  • CLI (prep, order, leaks) and a FastAPI server behind a Next.js 15 dashboard
  • POS adapters start at CSV so any export works today

Key Decisions & Trade-offs

  • No LLM required — forecasting and variance are statistics, and an operator should not need a GPU to prep
  • Self-hosted and Apache-2.0 so a single site can run it for the cost of a small VPS
  • CSV adapter first; every POS can export CSV, and named integrations can follow
  • Ship a demo dataset with planted leaks so the detector proves itself in one command
  • CLI and dashboard over the same core, so a kitchen can live in the terminal or the browser

Current Status

Public and open source (Apache-2.0) at github.com/rohitguta2432/ladle, installable via pip. CI green across Python 3.11, 3.12, and 3.13. ladle demo ingests a bundled 120-day dataset and surfaces both planted leaks at the top of the board; prep, order, leaks, API, and dashboard all working.

Roadmap

  • Square and Toast POS adapters beyond CSV
  • Multi-site rollups for small groups
  • Waste logging so measured waste feeds the same variance board

What I'd Improve Next

  • Seasonality and event handling in the forecaster
  • One-command deploy recipe for a small VPS

Explore More