Ladle — Open-Source Prep Forecasting and Food-Cost Leak Detection
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
- MyFinancial — Personal Financial Advisor — Financial planning in India is fragmented across banks, insurance, and tax documents.
- PropCheck — AI Property Trust Score for India — Indian property buyers lose lakhs to fraudulent listings on Magicbricks, 99acres, Housing.
- StellarMIND — Chat-to-SQL with RAG — Business users need to query databases without knowing SQL.
- ClinicAI — WhatsApp AI Clinic Assistant — India has 12 lakh+ small clinics running on phone calls and paper diaries.
- MicroItinerary — AI Travel Planner — Travel apps optimize for proximity and ratings.
- SanatanApp — Hindu Devotional App — Devotional users in India juggle 5+ separate apps for Chalisa, Gita, Aarti, Ramayan, and Mahabharat.
- SynFlow — Enterprise Intelligence Platform — Private deal networks rely on manual introductions and spreadsheets.
- FinBaby (Jama) — Personal Finance Tracker — Indian middle-class families track expenses across UPI apps, bank statements, and paper notebooks.
- RetailOS — Multi-Tenant Retail SaaS — Indian kirana stores and small retailers use paper registers or basic billing software with no inventory tracking, no GST compliance, and no offline support.
- TripHive — Offline-First Collaborative Trip Planner — Group trip planning is fragmented across WhatsApp, Google Docs, Maps, Splitwise, and email.
- ScamRakshak — On-Device AI Scam Detector — Indians lose thousands of crores annually to digital scams via WhatsApp, SMS, and social media.
- PaisaGuard — Family Budget Survival App — Middle-class families worldwide track expenses inconsistently — UPI apps show transactions but don't enforce budgets.
- rohitraj.tech — Engineering work is often invisible.
- Agent Autopsy — Forensic Debugger for Failed AI Agent Runs — Most AI agent failures are silent — the run completes, the status code is green, and the result is still wrong.
- tinyvoice — Fine-Tune a Model in Your Own Voice in an Afternoon — Training your own language model sounds like a PhD job that needs a GPU cluster, so most developers never try.
- snap3d — One Photo In, an Editable 3D Model Out — A photo shows you one side of an object; the other five sides are a guess.
- Agentic OS — Force-Directed Map of a 387-Skill Claude Code Setup — An agent setup grows one plugin at a time until it has hundreds of skills, and nobody can see what it actually contains.
- claude-autodev — Autonomous 8-Stage Dev Pipeline for Claude Code — Agentic coding tools stop at a diff.
- KisanSathi — Six AI Farm Experts, Keyless and Local — Farmer-facing AI tools die at the API-key step, answer in English, and hand back generic advice with no live numbers behind it.
- MarginChef — AI Agent That Finds a Restaurant's Margin Leaks — Restaurants run on 3-5% net margins while food costs are up roughly 35% since 2019, and most owners never see per-dish economics.
- Quorum — Deep-Research Agent Swarm with a Shared GraphRAG Brain — Most AI research tools are one model in a loop.
- RegexForge — Plain English to a Regex You Can Trust — Regex is not hard because the syntax is exotic.
- Skillet — Turn Any Docs Page Into an Installable Claude Code Skill — Agent skills are the fastest way to teach a coding agent a new tool, but writing a good SKILL.
- Casita — Design Your Home in 3D in the Browser — Home design tools want an install, a login, or a CAD background.
- VoxelForge — A Voxel Sandbox Engine Built Properly — Voxel sandboxes are the demo everyone builds with a coding agent right now, and almost all of them are a throwaway single HTML file that hitches on chunk generation, ships a texture pack, and cannot be read or extended.
- prompt-ocean — Type a Sea, Watch It Exist — Generative interfaces usually hand a model the wheel and hope.
- HEXAPOD — Inverse Kinematics and Gait Simulator — Hexapod gait and leg IK are usually explained with equations and a video, or hidden inside a robotics library.
- avatar-sync — Real-Time Face and Hand Tracking in One HTML File — Face and hand tracking demos come wrapped in a build step, a server, and usually an API key — which puts a wall in front of anyone who just wants to see what the models actually output before building on them.
- Reliability & Production Readiness — Load testing, observability, and API contracts.
- Open Source Repos — Browse the source code behind these projects.