OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Workflow Agents

Cookhero

CookHero is an open-source, self-hosted cooking and diet-management assistant that combines conversational recipe help, retrieval-augmented search, meal planning, food logging and nutrition analysis in an agent-based application.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Cookhero — OpenViST project profile in Workflow Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use CookHero when you want recipe assistance and diet tracking in the same self-hosted workflow, particularly when a weekly plan should connect to meal records and nutrition summaries.

Who it is for

  • Home cooks seeking conversational recipe and cooking guidance.
  • People planning meals around stated tastes, goals or dietary restrictions.
  • People who want to record meals and review estimated nutrition over time.
  • Developers interested in adapting an LLM cooking assistant with retrieval, tools and subagents.

Documented uses

  • Ask cooking, ingredient-pairing or nutrition questions in natural language.
  • Find recipes using the built-in collection or an uploaded personal Markdown recipe collection.
  • Create a weekly meal plan and organize meals by day and meal type.
  • Record meals from text or images and review estimated calories and macronutrients.
  • Compare planned meals with recorded intake in daily or weekly nutrition summaries.
Before you choose

Requirements & limits

The project is published as a public GitHub repository under the Apache-2.0 license. Its README documents self-hosted setup rather than a hosted service.

  • Local setup requires Python 3.12 or later and Node.js 18 or later; Docker and Docker Compose are recommended.
  • The listed application stack includes FastAPI, React, PostgreSQL, Redis, Milvus and MinIO.
  • Model, web-search and other integrations require configuration through environment variables and API keys where used.
  • The project describes nutrition values from meal text or images as estimates.
  • Image uploads are documented with a limit of four images, up to 10 MB each, for agent and diet-record scenarios.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up CookHero locally with Docker Compose

Prepare the documented local application stack and start its backend and frontend.

Before you start

  • Python 3.12 or later
  • Node.js 18 or later
  • Docker and Docker Compose are recommended
  • A project clone and configured environment variables, including necessary API keys

Steps

  1. Clone the CookHero repository and copy .env.example to .env; fill in the required API keys and configuration values.

  2. From the deployments directory, run docker-compose up -d to start the listed infrastructure services.

  3. Install the Python requirements, initialize the database with the command below, then start the backend with the documented Uvicorn command.

    Documented command
    python -m scripts.howtocook_loader

  4. In frontend, install dependencies with the command below and start the frontend with the command below.

    Documented command
    npm install
    Documented command
    npm run dev

Expected outcome

The README gives local frontend and backend addresses, plus an API documentation address.

Guide limitations

  • This is a setup procedure, not a compatibility or successful-execution guarantee.
  • The README requires API-key configuration but does not establish that every listed integration is needed for every use.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
Decade-qiu/CookHero · Official homepage title · retained in its source language
How we review sourcesSuggest a correction