MarginChef — AI Agent That Finds a Restaurant's Margin Leaks

Problem

Restaurants run on 3-5% net margins while food costs are up roughly 35% since 2019, and most owners never see per-dish economics. The leaks — a bestseller that bleeds, a price that never moved when its ingredients did — hide inside a POS export nobody reads.

Business Impact

An independent restaurant losing two points of margin to unrepriced dishes is losing real money every month it goes unnoticed. MarginChef converts a POS export into a ranked list of fixes with a rupee or dollar figure attached to each — the difference between knowing food costs are up and knowing which three dishes to reprice on Monday.

System Approach

• Plate costing: recipe times current ingredient prices gives true cost per dish
• Five leak detectors, each with an explicit monthly impact formula in leaks.py
• Menu engineering quadrants from popularity against margin
• Reprice suggestions snapped to .49 or .99 price points, capped at +15%, with projected monthly gain
• Local LLM writes a five-move action plan ranked by money at stake, with rule-based fallback
• CLI with analyze, report (shareable HTML), prices, and ask subcommands

Key Decisions & Trade-offs

• One leak per dish — overlapping detectors share a root cause, so the monthly total stays honest
• Keyless local LLM over a cloud API; a restaurant's cost sheet is not third-party data
• Rule-based fallback so a missing Ollama degrades the answer instead of breaking the tool
• Cap reprices at +15% and snap to familiar price points — advice a kitchen will actually run
• Plain CSVs as the interface so any POS export works without an integration

Current Status

Public and open source (MIT) at v0.2.0, installable with pip install -e . and runnable against the bundled sample_data in one command. All five detectors, menu quadrants, reprice suggestions, HTML report, and the ask subcommand ship working; pytest suite green.

Roadmap

• Direct POS connectors so the CSV step disappears
• Multi-period trend view to catch slow cost drift
• Supplier substitution suggestions for the worst-offending ingredients

What I'd Improve Next

• Currency and tax handling for multi-region kitchens
• A small web UI for owners who will not open a terminal

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