Skip to main content

Installation

See Installation Guide for npm, bunx, Docker, and development setup options.

Authentication

See Model Configuration for OAuth setup, API keys, and environment variable configuration.

Supported Models

AgentUse supports multiple AI providers with the format provider:model-name. Examples:
Any model available from Anthropic, OpenAI, OpenRouter, OpenCode Go, or Amazon Bedrock can be used. You can also specify custom API keys: anthropic:claude-sonnet-5:CUSTOM_API_KEY

Your First Agent

Create hello.agentuse:
Run it:

File System Agent

Create project-analyzer.agentuse:
Run it:
See Agent Syntax - MCP Servers for HTTP servers, environment variables, and tool restrictions.

Model Override

Override the model at runtime without editing agent files:
See CLI Commands - Model Override for format details, environment-specific keys, and sub-agent inheritance behavior.

Sub-agents Support

AgentUse supports calling other agents as sub-agents:

Remote Agents

You can run agents directly from HTTPS URLs:
Only HTTPS URLs with .agentuse extensions are supported for security. Always review remote agents before execution.

Environment Variables

Configure API keys and behavior via environment variables or .env files:
See Environment Variables Reference for all configuration options including custom API key suffixes, behavior control, and MCP server settings.

Schedule Your Agent

Add a schedule to run agents automatically:
Start the server to enable scheduling:
See Scheduled Agents Guide for cron expressions, intervals, and best practices.

What’s Next?

Creating Agents

Learn agent syntax

Examples

See more examples