OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Dexto

Dexto is a TypeScript agent harness with a CLI and SDKs for building AI applications. It orchestrates stateful agents, managing context, tools and recovery, and includes a coding agent accessible through CLI and Web UI.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Dexto — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Dexto when building an agent application that needs orchestration of model calls, state and tools, or when you want to start from its included coding agent.

Who it is for

  • Developers building custom AI agents or agentic applications.
  • Developers who want a coding agent to work with a codebase through a CLI or Web UI.

Documented uses

  • Define agents in YAML with a model, tools, storage and permissions.
  • Connect agents to MCP servers for tools such as filesystem access or browser automation.
  • Use the included coding agent to read, write and refactor code, run shell commands and tests, and delegate exploration or planning.
Before you choose

Requirements & limits

  • Dexto is a framework and harness: using it involves configuring an agent and its model and tools.
  • Model setup varies: listed hosted providers use API keys or cloud credentials, while local models require local installation or setup.
  • The coding agent is available through the CLI and Web UI; the project also describes SDKs for embedding agent development.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Connect MCP servers in an agent YAML configuration

Configure an agent with filesystem and browser MCP servers using the documented YAML pattern.

Before you start

  • Dexto
  • An agent YAML configuration file
  • npx available to invoke the configured server packages

Steps

  1. Add an mcpServers section to the agent YAML file.

  2. Add a filesystem server with type: stdio, command: npx, and arguments ['-y', '@modelcontextprotocol/server-filesystem', '.'].

  3. Add a browser server with type: stdio, command: npx, and arguments ['-y', '@anthropics/mcp-server-puppeteer'].

  4. Browse and add servers using the MCP Store in the Web UI or /mcp commands in the CLI.

Expected outcome

The agent YAML describes filesystem and browser MCP servers, and Dexto provides documented interfaces for browsing and adding servers.

Guide limitations

  • The source does not document a complete launch or validation procedure for this configuration.
  • Server access and behavior are not verified by these configuration steps.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
DextoDefine agents in YAML with a model, tools, storage and permissions.CLI
AgeniteDefine typed tools with JSON Schema validation and error handling.CLI
VeldraCreate an agent with a policy, tools, skills, knowledge base and reasoning method.Self-hostedThe documented deployment is self-hosted and uses a sign-in gate after a first-run administrator account is created.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
truffle-ai/dexto · Official homepage title · retained in its source language
How we review sourcesSuggest a correction