Running TazeAI Locally

This guide will set you up with running TazeAI locally. This involves a Next.js app, a Supabase backend, and the ability to run the dev containers with Codesandbox.

Prerequisites

These are the prerequisites for running TazeAI locally.

Bun - Enables running the monorepo
Docker - Enables running the Supabase backend

Setup

1. Clone the repository

git clone https://github.com/tazeai/tazeai.git
cd tazeai

2. Install dependencies

bun install

3. Run backend

Make sure you have Docker running from the instructions above.

bun backend:start

Grab the anon key and service role key from the output. We'll use these in step 5 and 7.

4. Get API keys

a. Get Codesandbox API key

Go to Codesandbox Dashboard
Click on setting in the right side menu, your workspace setting should open
Navigate to the "API" tab
Click "Create API Token" and generate an API token
Copy the token and save it for the environment setup step

Note: We plan on enabling running the dev containers with Docker Desktop in the future after we figure out the best API integration.

b. Get Anthropic API key

Request an API key from Anthropic. This is used for chatting with your project. https://console.anthropic.com/settings/keys

c. Get Fast Apply API key

For applying AI code, SOTA is to use fast apply models in order to resolve the code change. There are two options for Fast Apply providers:

You only need to get one of the keys and set it in the environment variables in later steps.

5. Set environment variables

Run the interactive environment setup script:

bun run setup:env

Note: If you'd prefer manually setting up the environment variables, see the appendix for instructions.

6. Initialize the database

Set up the database schema

bun db:push

7. Seed the database with test data

Seed the database with test data. This will create test users and projects.

bun db:seed

8. Run development server

bun dev

Go to http://localhost:3000 to see the app running. You're all set!

Now that you have TazeAI running locally, explore these resources to make your first contribution or learn more about the architecture. Understanding how TazeAI works will help you contribute more effectively to this visual editor for React and TailwindCSS.