The deployment platform for
Claude agents
Deploy Claude Agent SDK to production in seconds.
One command to production
cast deployPartnered with
Ship Claude agentsShip Claude Agent SDK with one command
Import Your Project
Import a Claude Agent SDK project from GitHub or generate a new agent from a prompt or template.
One click deploy
Click deploy or run cast deploy. Your agent runs in an auto-scaling sandbox with built-in logging and observability.
Iterate
View tool traces, inspect output logs, and refine your agent using real production data. Infrastructure scales automatically.
The easiest way to deploy agents with the Claude Agent SDK
Deploy your
first agent in
seconds
Deploy automatically from git or with our CLI
Isolated sandboxes for every agent execution
Observability for every run
Secure by default with isolated runtimes
Research Agents
Code Agents
DevOps Agents
Data Agents
Finance Agents
Customer Support Agents
Features
Long running, auto-scaling sandboxes
Deploy agents that run for hours or days in isolated sandboxes. Infrastructure scales on demand so you can focus on building, not babysitting.
MCP gateway
Skip the integration spaghetti. Our MCP gateway gives agents access to any tool or API while you control permissions from a single dashboard.
One click deploy
One click. Your Claude agent is live. Castari manages provisioning, versioning, and execution behind the scenes.
Agent observability
Full visibility into every agent decision. Trace tool calls, inspect outputs, and debug in real time—not after something breaks in production.
Model router
Use any model with the Claude Agent SDK—OpenAI, xAI, GLM, and more. Keep your agent code, swap the model. No rewrites required.
Start building
powerful agents
Get StartedFAQs
Castari is a deployment platform for Claude Agent SDK agents. Import your project, run cast deploy, and your agent is live with auto-scaling, logging, and observability built in.
No. Castari works with standard Claude Agent SDK code without modification. You keep full ownership of your codebase with zero vendor lock-in—if you ever want to self-host, your agents will run anywhere. We simply provide the infrastructure layer.
Deploying agents yourself means managing containers, configuring secure environments, handling scaling logic, and monitoring execution. Castari handles all of this out of the box with production-grade infrastructure and no DevOps overhead.
Every agent runs in an isolated sandbox environment. We use a variety of sandbox providers to ensure security and performance. The ability to select your own sandbox provider is coming soon.
Castari is free during our private beta. When we launch publicly, we'll use usage-based pricing—you'll pay only for the compute your agents use, not per seat or per agent.
Castari supports any model with the Claude Agent SDK—not just Claude. Use OpenAI, xAI, open source models, or any provider you prefer. Your agent code stays the same.
Getting started takes less than 5 minutes. Install the CLI with npm install -g @castari/cli, authenticate with cast login, and deploy your Claude Agent SDK agent using cast deploy. Your agent will immediately be accessible via REST API or our SDK.