Skip to main content

Overview

This guide will help you deploy Tesslate Studio on your own infrastructure. Whether it’s your local machine, a cloud server, or an on-premises datacenter, you’ll have complete control over your AI development environment.
Looking for the cloud version? Check out studio.tesslate.com for our hosted offering.

Prerequisites

Before you begin, ensure you have:

Docker Desktop

Windows/Mac: Download Docker DesktopLinux: curl -fsSL https://get.docker.com | sh

System Requirements

  • 8GB RAM minimum (16GB recommended)
  • 10GB disk space
  • Windows, Mac, or Linux

API Key

At least one AI provider:
  • OpenAI (GPT-5, GPT-4)
  • Anthropic (Claude)
  • Or use Ollama (free local models)

Git

Download from git-scm.com

Installation Steps

1

Clone the Repository

git clone https://github.com/TesslateAI/Studio.git
cd Studio
2

Create Environment Configuration

cp .env.example .env
3

Generate Secure Keys

Generate your secret keys using Python:
# Generate SECRET_KEY
python -c "import secrets; print(secrets.token_urlsafe(32))"

# Generate LITELLM_MASTER_KEY
python -c "import secrets; print('sk-' + secrets.token_urlsafe(32))"
Copy these keys for the next step.
4

Configure API Keys

Edit the .env file and add your credentials:
# Required: Application secret key
SECRET_KEY=your-generated-secret-key

# Required: LiteLLM master key
LITELLM_MASTER_KEY=sk-your-litellm-master-key

# Required: At least one AI provider API key
OPENAI_API_KEY=sk-your-openai-key
# OR
ANTHROPIC_API_KEY=sk-your-anthropic-key
If you prefer free local models:
  1. Install Ollama from ollama.ai
  2. Pull a model: ollama pull llama2
  3. Set in .env:
LITELLM_DEFAULT_MODELS=ollama/llama2
5

Start Tesslate Studio

docker compose up -d
This command will:
  • Pull required Docker images
  • Start all services (orchestrator, frontend, database, proxy)
  • Automatically seed the database with agents and templates
Wait about 30-60 seconds for all services to start.
6

Access the Application

Open your browser and navigate to:
http://studio.localhost
Can’t access studio.localhost?See Troubleshooting below.
7

Create Your Account

  1. Click “Sign Up” on the login page
  2. Enter your email and password
  3. The first user is automatically granted admin privileges
8

Create Your First Project

  1. Click “New Project”
  2. Choose a starter template:
    • Next.js 15 - Full-stack React with App Router
    • Vite + React + FastAPI - React frontend with Python backend
    • Vite + React + Go - React frontend with Go backend
  3. Give your project a name
  4. Click “Create”
Congratulations! Your self-hosted Tesslate Studio is now running.

Quick Test

Let’s verify everything is working:
1

Start Building

In the chat interface, type:
Create a simple todo app with add, delete, and mark complete functionality
2

Watch the AI Generate

The AI will generate React components and you’ll see your app appear in the live preview within seconds.
3

Make Changes

Try modifying the app:
Add a dark mode toggle button
Changes appear instantly in the preview!

Troubleshooting

Problem: studio.localhost doesn’t resolve or shows “connection refused”.Solutions:
  1. Check Docker is running:
    • Open Docker Desktop
    • Verify it says “Docker is running”
  2. Verify containers are running:
    docker compose ps
    
    All services should show “Up” status.
  3. Check logs for errors:
    docker compose logs orchestrator
    docker compose logs app
    
  4. Try localhost with port: Some systems need explicit port:
    http://localhost:80
    
  5. Restart everything:
    docker compose down
    docker compose up -d
    
Problem: Error says port 80 is already in use.Solution:
  1. Find what’s using port 80:
    # Windows:
    netstat -ano | findstr :80
    
    # Mac/Linux:
    lsof -i :80
    
  2. Stop the conflicting service or change Tesslate’s port: Edit docker-compose.yml:
    services:
      traefik:
        ports:
          - "8000:80"  # Change to port 8000
    
    Then access at: http://studio.localhost:8000
Problem: Errors about database connection failures.Solution:
# Stop everything
docker compose down

# Remove old database volume
docker volume rm tesslate-studio_postgres_data

# Start fresh
docker compose up -d
This will delete all existing data!
Problem: “Invalid API key” or “API key not found” errors.Solution:
  1. Verify your key is correct in .env
  2. Make sure there are no extra spaces or quotes
  3. Test the key with your provider’s website
  4. Restart the orchestrator:
    docker compose restart orchestrator
    
Problem: Projects fail to start or show “development server error”.Solution:
  1. Check Docker disk space:
    docker system df
    
  2. Clean up unused containers/images:
    docker system prune -a
    
  3. Check orchestrator logs:
    docker compose logs orchestrator | grep -i error
    

What’s Included

After installation, you’ll have:

10 AI Agents

Pre-installed agents for different tasks:
  • Stream Builder
  • Full Stack Agent
  • Code Analyzer
  • Test Generator
  • API Designer
  • And 5 more!

3 Project Templates

Production-ready starter templates:
  • Next.js 15 (App Router)
  • Vite + React + FastAPI
  • Vite + React + Go

Live Preview

Real-time preview with hot module replacement

Monaco Editor

VSCode-like code editor in the browser

GitHub Integration

Import, edit, and commit to GitHub repos

Architecture Diagrams

Auto-generated architecture visualizations

Development Mode

For active development with hot reload:

Stopping Tesslate Studio

docker compose down

Next Steps

Getting Help