@toolhouseai/cli
v1.5.11
Published
Toolhouse CLI for building, running, and deploying AI and agents
Downloads
43
Maintainers
Readme
Toolhouse CLI
A powerful command-line interface tool for managing and deploying intelligent agents. Streamline your development workflow with simple, intuitive commands for agent creation, execution, and deployment.
Prerequisites
- Node.js 14.0 or higher
- npm 6.0 or higher
Installation
# Global installation of the cli
npm install @toolhouseai/cli -g
# Now it's available globally as: thUsage
Authorize the CLI
This step will auth th with the Toolhouse backend:
# Login into toolhouse to run and deploy agents
th loginCreate a New Agent
Create agents with customizable templates and configurations:
# Generate an agent with an auto-generated name
th new
# Create an agent with a custom name
th new my-agentRun Agents
Execute agents locally for testing and development:
# Run a specific agent NOTE: the .yaml extension in this command
th run my-agent.yamlDeploy Agents
Deploy agents to your production environment:
# Deploy a specific agent
th deploy my-agent.yamlRAG Commands
Manage your RAG (Retrieval-Augmented Generation) folders and files:
# List all RAG folders
th rag ls
# List files in a specific RAG folder
th rag ls my-folder
# Create a new RAG folder
th rag create my-folder
# Add files to a RAG folder
th rag add my-folder file1.txt file2.pdf
# Delete a RAG folder
th rag rm my-folderNote: to add RAG functionalities to your agent you have to make sure you also add a row to your agent file. Example:
#
# Your agent file content here
#
rag: my-folderDocumentation
For detailed documentation and advanced usage examples, visit our official documentation.
GitHub Actions Integration
Automate your agent deployment pipeline using our GitHub Actions workflow. See the example configuration in .github/workflows/deploy-agents.yml.
Contributing
We welcome contributions! Please see our Contributing Guide for details.
License
This project is licensed under the MIT License - see the LICENSE file for details.
