Skip to main content

​
General Questions

Tesslate Studio is an open-source AI-powered development platform that helps you build full-stack web applications using natural language. It’s designed to be self-hosted, giving you complete control over your development environment and data.Key features:
  • AI code generation from natural language
  • Live preview with hot reload
  • Self-hosted infrastructure
  • Container isolation for projects
  • Support for multiple AI models
Yes! Tesslate Studio is 100% open source under the Apache 2.0 license. You can:
  • Use it for free (personal or commercial)
  • Self-host on your own infrastructure
  • Modify and customize it
  • Fork and distribute it
You only pay for:
  • Infrastructure costs (if deploying to cloud)
  • AI API usage (OpenAI, Anthropic, etc.) OR use free local models with Ollama
Data Sovereignty:
  • Your code never leaves your infrastructure
  • Complete control over data storage
  • No vendor lock-in
Cost Control:
  • No per-seat pricing
  • Pay only for infrastructure and AI APIs
  • Use free local models (Ollama)
Customization:
  • Fork and modify the platform
  • Create custom agents
  • Add proprietary features
Self-Hosting:
  • Deploy anywhere (laptop, cloud, on-prem)
  • Works offline (with local models)
  • No internet dependency for core features
Not necessarily! You have three options:1. Bring Your Own API Keys (BYOK)
  • Use OpenAI, Anthropic, Google Gemini, etc.
  • Pay your provider directly (typically pennies per request)
2. Local Models (Free)
  • Install Ollama
  • Use free models like Llama 2, Mistral, CodeLlama
  • 100% offline, zero AI costs
3. Hybrid Approach
  • Use local models for development
  • Use cloud models for production
  • Best of both worlds
Yes! The Apache 2.0 license allows:
  • Commercial use
  • Building paid products with it
  • Using it for client work
  • Selling hosting services
  • Creating proprietary extensions
No restrictions on:
  • Number of users
  • Revenue generated
  • Type of business

​
Technical Questions

Frontend:
  • React 19
  • TypeScript
  • Vite 7
  • Tailwind CSS
  • Monaco Editor (VSCode engine)
Backend:
  • FastAPI (Python)
  • PostgreSQL
  • SQLAlchemy ORM
  • Docker SDK
  • LiteLLM (AI gateway)
Infrastructure:
  • Docker / Docker Compose
  • Traefik (reverse proxy)
  • Node.js (for project runtimes)
Minimum:
  • 8GB RAM
  • 10GB disk space
  • Docker Desktop (or Docker Engine on Linux)
  • Modern browser (Chrome, Firefox, Safari, Edge)
Recommended:
  • 16GB RAM
  • 20GB disk space
  • Fast internet (for AI API calls)
Supported Operating Systems:
  • Windows 10/11
  • macOS 12+
  • Linux (Ubuntu, Debian, Fedora, etc.)
Not recommended, but possible. Docker provides:
  • Easy setup
  • Container isolation
  • Consistent environment
  • Project sandboxing
Without Docker, you need to manually:
  • Install PostgreSQL
  • Configure Traefik or NGINX
  • Set up Node.js environments
  • Manage project isolation
For most users, Docker is much simpler.
Tesslate Studio supports 100+ AI models via LiteLLM:Cloud Providers:
  • OpenAI (GPT-5, GPT-4, GPT-3.5)
  • Anthropic (Claude 3.5, Claude 3)
  • Google (Gemini Pro, Gemini Flash)
  • Azure OpenAI
  • Cohere
  • Together AI
  • And many more
Local Models:
  • Ollama (Llama 2, Mistral, CodeLlama, etc.)
  • LM Studio
  • Any OpenAI-compatible endpoint
No. Tesslate Studio is self-hosted—everything runs on YOUR infrastructure:
  • Code stays on your machine/server
  • Database is local
  • No telemetry or tracking
  • No external dependencies (except AI APIs if you choose to use them)
We never see:
  • Your code
  • Your data
  • Your prompts
  • Your API keys
Absolutely! All agents are open source. You can:
  • Fork existing agents
  • Modify system prompts
  • Change agent behavior
  • Swap AI models
  • Create entirely new agents
See Creating Custom Agents for details.

​
Deployment Questions

Anywhere that runs Docker:Local:
  • Your laptop/desktop
  • Home server
  • Raspberry Pi (with sufficient RAM)
Cloud:
  • AWS (EC2, ECS, Fargate)
  • Google Cloud (Compute Engine, Cloud Run)
  • Azure (VM, Container Instances)
  • DigitalOcean Droplets
  • Hetzner, Linode, etc.
On-Premises:
  • Company datacenter
  • Private cloud
  • Air-gapped networks (with local AI models)
Yes! Configure in .env:
APP_DOMAIN=studio.yourcompany.com
APP_PROTOCOL=https
Projects will be at:
  • studio.yourcompany.com - Main app
  • project-name.studio.yourcompany.com - User projects
See Deployment Guide for SSL setup.
For production deployments:
  1. Get a domain (e.g., studio.yourcompany.com)
  2. Point DNS to your server
  3. Configure Traefik for automatic Let’s Encrypt:
# docker-compose.yml
services:
  traefik:
    command:
      - "--certificatesresolvers.letsencrypt.acme.email=admin@yourcompany.com"
      - "--certificatesresolvers.letsencrypt.acme.storage=/letsencrypt/acme.json"
Traefik automatically gets and renews SSL certificates!See Deployment Guide for full instructions.
Yes! Set DATABASE_URL in .env:
DATABASE_URL=postgresql+asyncpg://user:pass@your-db-host:5432/tesslate
Supported:
  • AWS RDS
  • Google Cloud SQL
  • Azure Database for PostgreSQL
  • Managed PostgreSQL providers
  • Self-hosted PostgreSQL
Requirements:
  • PostgreSQL 13+
  • Public accessibility or VPN connection
Small Team (1-10 users):
  • 2 vCPUs
  • 8GB RAM
  • 50GB SSD
  • Estimated cost: $40-80/month on cloud
Medium Team (10-50 users):
  • 4 vCPUs
  • 16GB RAM
  • 100GB SSD
  • Estimated cost: $80-160/month on cloud
Large Team (50+ users):
  • 8+ vCPUs
  • 32GB+ RAM
  • 200GB+ SSD
  • Consider load balancing
  • Estimated cost: $200+/month on cloud
Note: Costs vary by cloud provider

​
Usage Questions

Primary Focus:
  • React + TypeScript (frontend)
  • JavaScript/TypeScript (full-stack)
Backend Options (via templates):
  • Python (FastAPI, Flask, Django)
  • Go
  • Node.js (Express, Next.js API routes)
AI agents can generate code in any language, but templates and tooling are optimized for JavaScript/TypeScript.
Yes! Multiple ways:1. GitHub Import
  • Connect GitHub account
  • Import any public/private repository
  • Automatically creates project container
2. Manual Upload
  • Create blank project
  • Upload files via code editor
  • Or use GitHub integration
3. Git Clone
  • Create project
  • Use integrated terminal to clone repo
Currently: Tesslate Studio is designed for individual users with isolated projects.Planned Features:
  • Real-time collaboration
  • Multiplayer editing
  • Shared projects
  • Team workspaces
Workaround:
  • Use GitHub for collaboration
  • Each team member has their own Tesslate instance
  • Share via Git commits
Multiple options:1. GitHub Integration
  • Push to GitHub repository
  • Clone repository elsewhere
2. Download Files
  • Use code editor to select files
  • Download individual files or folders
3. Docker Container Export
docker cp <container-id>:/app ./my-project
4. Git Clone
  • Projects are Git repositories
  • Clone from container
When you delete a project:
  1. Database record is removed
  2. Docker container is stopped and deleted
  3. All project files are deleted
This is permanent and cannot be undone.Best practices:
  • Push to GitHub before deleting
  • Download files locally
  • Export container if needed
Partially:What works offline:
  • Core application
  • Code editor
  • Live preview
  • Project management
  • If using Ollama: AI generation works offline
What requires internet:
  • Cloud AI models (OpenAI, Anthropic, etc.)
  • GitHub integration
  • npm package installs
  • External API calls from your projects
For full offline: Use Ollama with local models.

​
Troubleshooting

Try these steps:
  1. Refresh the preview: Click refresh button in preview panel
  2. Check for errors: Open browser console (F12) and look for errors
  3. Restart dev server: Go to Settings → Restart Development Server
  4. Check container logs: 
    docker compose logs <project-container-id>
  5. Clear browser cache: Hard refresh (Ctrl+Shift+R or Cmd+Shift+R)
Common causes:1. Invalid API key
  • Check .env file
  • Verify key with provider
  • Restart orchestrator
2. Rate limiting
  • You’ve hit API rate limits
  • Wait and try again
  • Or switch to different model
3. Model not available
  • Model might be deprecated
  • Try a different model
  • Check LiteLLM compatibility
4. Network issues
  • Check internet connection
  • Verify firewall rules
  • Check Docker networking
Solutions:1. Check Docker is running
  • Open Docker Desktop
  • Verify status is “Running”
2. Check containers are up
docker compose ps
All should show “Up”3. Try with port
http://localhost:80
4. Check /etc/hosts (Mac/Linux) Add this line if missing:
127.0.0.1 studio.localhost
5. Check Windows hosts file File: C:\Windows\System32\drivers\etc\hosts Add:
127.0.0.1 studio.localhost
6. Restart everything
docker compose down
docker compose up -d

​
Security & Privacy

Security features:
  • JWT authentication with refresh tokens
  • Bcrypt password hashing
  • Encrypted credential storage (GitHub tokens, API keys)
  • Container isolation per project
  • Command validation for AI agents
  • Audit logging of all operations
  • HTTPS/TLS support in production
Best practices:
  • Use strong passwords
  • Enable HTTPS in production
  • Keep Docker updated
  • Regular database backups
  • Monitor audit logs
See Security Best Practices for details.
No. AI agents are sandboxed:
  • Can only access the project’s container
  • Cannot access host file system
  • Cannot access other containers
  • Commands are validated before execution
Blocked operations:
  • File system access outside container
  • Network access to local services
  • Dangerous shell commands
  • System modifications
Database (PostgreSQL):
  • User passwords: Bcrypt hashed
  • GitHub tokens: Fernet encrypted
  • API keys: Fernet encrypted
  • Refresh tokens: Stored with revocation support
Environment (.env):
  • SECRET_KEY: Keep secure, never commit
  • AI provider keys: Keep secure, never share
Best practices:
  • Use strong SECRET_KEY
  • Don’t commit .env to Git
  • Rotate keys regularly
  • Use different keys for dev/prod

​
Getting Help

Documentation

Browse the full documentation

GitHub Discussions

Ask questions and share ideas

GitHub Issues

Report bugs and request features

Email Support

Direct support (response within 24h)

​
Still Have Questions?

Ask in Discussions

Can’t find your answer? Ask the community in GitHub Discussions.