GetWebstack logo

Your dev environment,
up and running with zero config

Isolated sandboxes that scale from a solo developer to a fleet of AI agents.

curl -sSL https://getwebstack.com/install.sh | bash
Get started freeSee how it works

No credit card required  ·  Locally or on your own cluster.  ·  Works on macOS, Linux, Windows

The problem

Sound familiar?

  • The morning setup ritual.

    Before writing a single line of code, you've already lost 30 minutes to services, ports, and databases that won't start.

  • "It works on my machine."

    Local drifts from production. You ship, it breaks. Nobody knows why.

  • Your AI agent codes blind.

    No running environment means no real feedback. Agents iterate on assumptions, not reality.

How does it work?

Steps to launch an app

curl -sSL https://getwebstack.com/install.sh | bash
#Analyze project and generate config
$ gws init
> Scanning project structure...
> Detected services: frontend (React), api (Node.js)
> Detecting dependencies... Adding PostgreSQL
> Configuring services...
> Setting up infrastructure...
> Creating AI agent instructions...
> Writing gws.json...
✔ Project initialized. Run "gws up" to deploy.

Step 1 one time only

gws init  # we learn your project
    Scans your repo. Detects services, frameworks, databases. Generates Dockerfiles, Kubernetes manifests, and AI agent instructions automatically. You touch nothing.
Get startedSee docs

STEP 2

gws up  # everything starts
    Your full stack spins up locally: frontend, backend, database, HTTPS, routing. One URL. Ready in seconds. Production parity, without the production.
Get startedSee docs
#Start local cluster
$ gws up
> Creating cluster "myapp"...
> Deploying services locally...
✔ Cluster ready at https://myapp.local.getwebstack.dev

#Or deploy to your own cluster
$ gws up --cluster my-k8s-cluster
✔ Deployed to on-premise cluster
#Add MCP server to your config
$ gws mcp install
> Adding GetWebStack MCP server...
> Updating claude_desktop_config.json
✔ MCP server installed

STEP 3 optional

gws up -w feature-x  # spin up a parallel environment
    Need to work on two features at once? Hand off a worktree to an AI agent? Run E2E tests in isolation? Each worktree gets its own full environment on the same cluster. No conflicts. No teardowns.
Get startedSee docs

Who it's for

Built for developers and teams. Ready for AI agents

For developers & engineers
  • One command starts your entire stack — every morning, no ritual
  • Test in an environment that mirrors production exactly
  • Works for any stack: Go, Python, Node, Rails, Django, React and more
  • New team member onboards in minutes, not days
For AI-forward teams
  • Each AI agent gets its own isolated sandbox with a full running stack
  • Run multiple agents in parallel on the same cluster, zero conflicts
  • MCP-native: works with Claude, Cursor, Codex, and any MCP-compatible agent
  • Plug into CI/CD: E2E tests, PR previews, automated validation on every push

USE CASES

One tool. Every environment scenario.

  • Local dev.

    Your whole stack, every morning, one command

  • AI agents

    Every agent gets its own sandbox to test its own work.

  • Parallel development

    10 features. 10 environments. Zero conflicts.

  • E2E testing

    Run your full test suite against a real stack, not mocks.

  • PR previews

    Every PR gets its own isolated environment, automatically.

  • Onboarding

    New developer productive on day one, not day three.

SUPPORT

  • Community

    We are here to make sure you develop quickly and don't get stuck.

    Join our Discord community

  • Documentation

    Check our detailed documentation that guides you to set up, develop and optimize your app.

    See docs

Blog

Check our blog for examples and news

  • woman learning

    3 steps to easily validate your SAAS idea without an MVP

    Read more
  • SAAS technologies

    How to choose your tech stack for your SAAS business

    Read more
  • Monolith to microservices

    Micro-apps vs Microservice vs Micro-frontends

    Read more

FAQ

Ask us anything

  • What is GetWebstack?

    A CLI that analyzes your project and spins up a full production-like environment in one command — with isolated sandboxes that scale from a solo developer to a fleet of AI agents. Runs locally or on your own infrastructure.

  • Who is it for?

    Any developer who loses time to environment setup. Solo devs, engineering teams, data scientists, and AI-forward teams running coding agents in parallel. If you have a project that needs to run, GWS gets it running.

  • Why should I use it?

    Because setting up a dev environment shouldn't take hours. One command replaces your entire setup process — for developers, E2E testing, and AI agents that need a real environment to validate their work.

  • How does zero config work?

    Run gws init in your project. GWS detects your stack and generates everything needed to run your environment. Currently supports all JavaScript, TypeScript, Python, and Go frameworks.
    Check our Git templates for each project. More frameworks are on the way.

  • Is it secure?

    Your source code never leaves your machine. Everything runs locally or on your own cluster — no cloud dependency, no third-party access to your code.

  • What AI agents work with it?

    MCP support is on our roadmap. Currently, AI agents interact with GWS through the CLI directly.
    gws up -w <branch> spins up an isolated sandbox any agent can work against.
    Join our Discord to follow MCP progress and get early access when it ships.

  • Can multiple developers share the same cluster?

    Yes. When running on a shared on-premise cluster, each developer or AI agent gets their own isolated worktree and sandbox, so everyone works in parallel without conflicts. For local clusters, each developer runs their own independent instance.

Stop setting up environments.
Start shipping.

Isolated sandboxes. No setup.

Get Started FreeRead the Docs

No credit card required.