Configuring Agents in Dexto

📄️ Overview

Dexto's power comes from its customizability. You can customize every part of your Dexto agent with one yml config file.

Complete reference for all agent.yml configuration options.

Configure the language model provider and settings for your Dexto agent.

Configure how your Dexto agent behaves and responds through system prompts that define personality, capabilities, and guidelines.

Configure the memory system to store and retrieve persistent information about user preferences, context, and important facts across conversations.

Configure Model Context Protocol (MCP) servers to extend your agent's capabilities by connecting to external tools, services, and APIs.

Control how and when users are prompted to approve tool execution through Dexto's flexible confirmation system.

Configure how your Dexto agent stores data: cache, database, and blob storage.

Configure session management for your Dexto agent, including maximum concurrent sessions and session timeouts.

Enable distributed tracing to monitor agent behavior, debug issues, and track performance using OpenTelemetry.

Extend agent behavior with custom logic that runs at specific points in the request/response lifecycle.

Configure built-in Dexto capabilities that provide core agent functionality like file operations, code search, and command execution.

Configure your agent's public metadata for Agent-to-Agent (A2A) communication and service discovery.

What are Internal Resources?

Configure and manage runtime changes to agent state through the AgentStateManager.