BigFood
Run the following command in DeepSeek Harness:
dsh plugin install kobenfang/BigFood
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install kobenfang/BigFood in DeepSeek Harness, source code at https://github.com/kobenfang/BigFood.
About this plugin
Staring into your fridge, overwhelmed by a variety of ingredients but unsure of what to cook? BigFood is designed to solve the modern kitchen's "decision fatigue." By leveraging advanced multimodal models, simply snap a photo of your ingredients, and the system automatically recognizes your inventory, whether it's fresh produce or leftovers. Crucially, it breaks the limitation of single ingredients, supporting multi-image mixing to intelligently generate creative recipes based on what you already have.
Whether you are a busy professional, a health-conscious homemaker, or a food enthusiast dedicated to reducing waste, BigFood is your thoughtful cooking assistant. It not only solves the "what to eat" dilemma but also helps track your stock via ingredient management and sends shopping alerts when items are running low. Say goodbye to takeout and duplicate purchases, and let AI serve as your private kitchen butler to seamlessly bridge the gap from "ingredient recognition" to a delicious meal.
Use Cases
- Staring at the fridge full of ingredients unsure of how to combine them
- Wanting to cook a new meal using leftover ingredients
- Needing to track and manage household ingredient inventory
Best For
- Busy office workers who often forget what to buy
- Foodies who love making "mixed dishes" but lack cooking inspiration
- Environmentalists who want to reduce food waste
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.