Prerequisites
Before you begin, make sure you have:
- A Crewship account (sign up here)
- An agent project ready to deploy — CrewAI, LangGraph, or LangGraph.js
Don’t have a project yet? Clone one of our quickstart repos and deploy it in minutes: Install the CLI
curl -fsSL https://www.crewship.dev/install.sh | bash
Invoke-WebRequest -Uri "https://api.crewship.dev/cli/releases/latest/download?platform=windows-x64" -OutFile "$env:LOCALAPPDATA\Programs\crewship.exe"
[Environment]::SetEnvironmentVariable("Path", "$([Environment]::GetEnvironmentVariable('Path', 'User'));$env:LOCALAPPDATA\Programs", "User")
Authenticate
Login to connect the CLI to your Crewship account:
This opens a browser window to authenticate. Once complete, your credentials are stored locally.
Run crewship whoami to verify your authentication status.
Add Crewship Configuration
Crewship currently supports CrewAI, LangGraph, and LangGraph.js. If you already have a project in one of these frameworks, you can deploy it on Crewship.
If you want to deploy an agent built with a framework that we don’t (yet) support, please send us a message at mail@crewship.dev so we can prioritize it!
Initialize a crewship.toml file in your project:
This auto-detects your framework and entrypoint:
CrewAI
LangGraph
LangGraph.js
🔍 Initializing Crewship project in /path/to/my_crew
Found pyproject.toml, reading project info...
Detected CrewAI project
Detected entrypoint: my_crew.crew:MyCrew
✅ Created crewship.toml
🔍 Initializing Crewship project in /path/to/my_agent
Found langgraph.json, reading project info...
Detected LangGraph project
Detected entrypoint: src.my_agent.graph:graph
✅ Created crewship.toml
🔍 Initializing Crewship project in /path/to/my_agent
Found langgraph.json, reading project info...
Detected LangGraph.js project
Detected entrypoint: ./src/graph.ts:graph
✅ Created crewship.toml
The init command automatically finds your entrypoint. You can also create crewship.toml manually — see the configuration reference. Deploy
Deploy your crew with a single command:
You’ll see output like:
📦 Packaging crew...
☁️ Uploading build context...
🔨 Building image...
✅ Deployed successfully!
Deployment: dep_abc123xyz
Production URL: https://my-crew.crewship.run
You can also simply run crewship deploy in a new project, and it will log you in and initialize the project configuration automatically.
Invoke Your Agent
Run your deployed agent:
crewship invoke --input '{"topic": "AI agents"}'
Stream Events
Watch your agent execute in real-time:
crewship invoke --input '{"topic": "AI agents"}' --stream
▶ Run started: run_xyz789
├─ [10:30:01] Starting execution
├─ [10:30:02] Agent: Researcher starting task...
├─ [10:30:25] Agent: Researcher completed task
├─ [10:30:26] Agent: Writer starting task...
├─ [10:30:58] Agent: Writer completed task
├─ [10:30:59] Artifact: report.md (2.4 KB)
✅ Run completed in 58.4s
View in Console
Open the Crewship Console to:
- View run history and logs
- Download artifacts
- Manage environment variables
- Monitor usage and costs
Next Steps
