Daita Logo

Daita CLI

The daita command-line tool for managing, deploying, and observing your hosted AI agents.

#What is daita-cli?

daita-cli is the standalone command-line interface for the Daita platform. It handles the full agent lifecycle — scaffolding projects, deploying to the cloud, running agents remotely, and observing executions, traces, and memory from your terminal.

The CLI is a separate package from daita-agents and can be installed on its own without the full agent framework. It ships as a core dependency of daita-agents, so if you have the framework installed you already have it.

#Installation

bash
# Standalone — no agent framework required
pip install daita-cli
 
# Or as part of the full framework
pip install daita-agents

#Authentication

All cloud commands require an API key from the Daita dashboard. Set it as an environment variable:

bash
export DAITA_API_KEY=your_api_key

Or place it in a .env file at the root of your project — the CLI loads it automatically.

#Global Options

These flags are available on every command:

FlagShortDescription
--output-oOutput format: text (default), json, or table
--verbose-vEnable verbose output
--quiet-qSuppress non-error output
--versionPrint the CLI version and exit
bash
# Machine-readable output
daita executions list --output json
 
# Verbose mode for debugging
daita push --verbose

#MCP Server

The CLI includes a built-in Model Context Protocol server that exposes your deployed agents as tools for coding assistants like Claude, Cursor, and others.

bash
daita mcp-server

Configure it in your MCP client (e.g., Claude Desktop claude_desktop_config.json):

json
{
  "mcpServers": {
    "daita": {
      "command": "daita",
      "args": ["mcp-server"],
      "env": {
        "DAITA_API_KEY": "your_api_key"
      }
    }
  }
}

Once connected, your coding assistant can invoke any deployed agent as a tool.

#Command Reference

CommandDescription
daita initScaffold a new Daita project
daita createAdd an agent or workflow to a project
daita testRun agents and workflows locally
daita pushDeploy the current project to the cloud
daita runExecute a deployed agent or workflow
daita executionsManage and inspect executions
daita statusShow project and deployment status
daita logsView deployment logs
daita agentsList and inspect deployed agents
daita deploymentsManage deployments
daita tracesView execution traces and spans
daita memoryInspect agent memory
daita conversationsManage conversation history
daita schedulesPause and resume scheduled agents
daita secretsManage encrypted cloud secrets
daita webhooksView webhook URLs