Deutsch | English | Español | français | 日本語 | 한국어 | Português | Русский | 中文

An open agent harness for AI applications—ships with a powerful coding agent.

What is Dexto?

Dexto is an agent harness—the orchestration layer that turns LLMs into reliable, stateful agents that can take actions, remember context, and recover from errors.

Think of it like an operating system for AI agents:

| Component | Analogy | Role | |-----------|---------|------| | LLM | CPU | Raw processing power | | Context Window | RAM | Working memory | | Dexto | Operating System | Orchestration, state, tools, recovery | | Your Agent | Application | Domain-specific logic and clients |

Why Dexto?

• Configuration-driven: Define agents in YAML. Swap models and tools without touching code.
• Batteries included: Session management, tool orchestration, memory, multimodal support, and observability—out of the box.
• Run anywhere: Local, cloud, or hybrid. CLI, Web UI, REST API, Discord, Telegram, or embedded in your app.

What You Can Build

• Coding Agents – Build, debug, and refactor code autonomously
• Autonomous Agents – Plan, execute, and adapt to user goals
• Digital Companions – Assistants that remember context and anticipate needs
• MCP Clients & Servers – Connect tools, files, APIs via Model Context Protocol
• Multi-Agent Systems – Agents that collaborate, delegate, and solve complex tasks together

Coding Agent

Dexto ships with a production-ready coding agent you can use immediately via the CLI or Web UI.

# Launch the coding agent (default)
dexto
Or explicitly
dexto --agent coding-agent

What it can do:

• Build new apps from scratch
• Read, write, and refactor code across your entire codebase
• Execute shell commands and run tests
• Spawn specialized sub-agents for exploration and planning
• Remember context across sessions with persistent memory
• Work with any of 50+ LLMs (swap models mid-conversation)

• Web UI – Chat interface with file uploads, syntax highlighting, and MCP tool browser
• CLI – Terminal-native with /commands, streaming output, and session management

Quick Start

Install

# macOS / Linux / WSL (native installer, recommended)
curl -fsSL https://dexto.ai/install | bash
Windows PowerShell
irm https://dexto.ai/install.ps1 | iex
Or build from source
git clone https://github.com/truffle-ai/dexto.git
cd dexto && pnpm install && pnpm install-cli

Upgrade/uninstall and migration troubleshooting live in docs:

• Installation guide: https://cli.dexto.ai/docs/getting-started/installation
• CLI command reference: https://cli.dexto.ai/docs/guides/cli/overview

Run

# Start Dexto (launches setup wizard on first run)
dexto

More options:

dexto --mode cli                                   # Terminal mode
dexto -p "create a landing page for a coffee shop" # One-shot task
dexto --auto-approve "refactor this codebase"      # Skip confirmations
dexto -m claude-sonnet-4-5-20250929                # Switch models
dexto --help                                       # Explore all options

Inside the interactive CLI, type / to explore commands—switch models, manage sessions, configure tools, and more.

Manage Settings

# Configure defaults like LLM provider/model, API keys, or download local models
dexto setup

Logs are stored in ~/.dexto/logs/. Use DEXTO_LOG_LEVEL=debug for verbose output.

Core Features

50+ LLMs, Instant Switching

Switch models mid-conversation—no code changes, no restarts.

| Provider | Models | |----------|--------| | OpenAI | gpt-5.2, gpt-5.2-pro, gpt-5.2-codex, o4-mini | | Anthropic | Claude Sonnet, Opus, Haiku (with extended thinking) | | Google | Gemini 3 Pro, 2.5 Pro/Flash | | Groq | Llama 4, Qwen, DeepSeek | | xAI | Grok 4, Grok 3 | | Local | Ollama, GGUF via node-llama-cpp (Llama, Qwen, Mistral, etc.) | | + Gateways | OpenRouter, AWS Bedrock, Vertex AI, LiteLLM |

Run locally for privacy: Local models keep data on your machine with automatic GPU detection (Metal, CUDA, Vulkan).

MCP Integration (30+ Tools)

Connect to Model Context Protocol servers—Puppeteer, Linear, ElevenLabs, Firecrawl, Sora, and more.

# agents/my-agent.yml
mcpServers:
  filesystem:
    type: stdio
    command: npx
    args: ['-y', '@modelcontextprotocol/server-filesystem', '.']
  browser:
    type: stdio
    command: npx
    args: ['-y', '@anthropics/mcp-server-puppeteer']

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

Human-in-the-Loop Controls

Fine-grained control over what your agent can do:

permissions:
  mode: manual           # Require approval for each tool
  # mode: auto-approve   # Trust mode for local development
  toolPolicies:
    alwaysAllow:
      - mcp--filesystem--read_file
      - mcp--filesystem--list_directory

Agents remember which tools you've approved per session.

Persistent Sessions & Memory

Conversations persist across restarts. Create memories that shape agent behavior.

# Continue last conversation
dexto -c
Resume specific session
dexto -r session-abc123
Search across all conversations
dexto search "database schema"

Multi-Agent Systems

Agents can spawn specialized sub-agents to handle complex subtasks. The coding agent uses this to delegate exploration:

# In your agent config
tools:
  - type: agent-spawner
    allowedAgents: ["explore-agent"]
    maxConcurrentAgents: 5
    defaultTimeout: 300000  # 5 minutes

Built-in sub-agents:

• explore-agent – Fast, read-only codebase exploration

Sub-agents run ephemerally, auto-cleanup after completion, and forward tool approvals to the parent—so users see one unified approval flow.

Run Modes

| Mode | Command | Use Case | |------|---------|----------| | Web UI | dexto | Chat interface with file uploads (default) | | CLI | dexto --mode cli | Terminal interaction | | Web Server | dexto --mode server | REST & SSE APIs | | MCP Server | dexto --mode mcp | Expose agent as an MCP server over stdio |

Platform integrations: Discord, Telegram

dexto --mode mcp --auto-approve --no-elicitation                # Default agent
dexto --mode mcp --agent coding-agent --auto-approve --no-elicitation
npx dexto --mode mcp --agent coding-agent --auto-approve --no-elicitation

{
  "command": "npx",
  "args": ["-y", "dexto", "--mode", "mcp", "--agent", "coding-agent", "--auto-approve", "--no-elicitation"]
}

dexto --mode server --port 3001
ngrok http 3001  # Optional: expose publicly

Dexto Agents SDK

Build AI agents programmatically. Everything the CLI does, your code can too.

npm install @dexto/core

import { DextoAgent } from '@dexto/core';
const agent = new DextoAgent({
  llm: { provider: 'openai', model: 'gpt-5.2', apiKey: process.env.OPENAI_API_KEY }
});
await agent.start();
const session = await agent.createSession();
const response = await agent.generate('What is TypeScript?', session.id);
console.log(response.content);
// Streaming
for await (const event of await agent.stream('Write a story', session.id)) {
  if (event.name === 'llm:chunk') process.stdout.write(event.content);
}
// Multimodal
await agent.generate([
  { type: 'text', text: 'Describe this image' },
  { type: 'image', image: base64Data, mimeType: 'image/png' }
], session.id);
// Switch models mid-conversation
await agent.switchLLM({ model: 'claude-sonnet-4-5-20250929' });

Start a server programmatically:

Start a Dexto server programmatically to expose REST and SSE streaming APIs to interact and manage your agent backend.

import { DextoAgent } from '@dexto/core';
import { loadAgentConfig, startHonoApiServer } from 'dexto';
const config = await loadAgentConfig('./agents/my-agent.yml');
const agent = new DextoAgent(config);
const { server } = await startHonoApiServer(agent, 3001);
// POST /api/message, GET /api/sessions, etc.

This starts an HTTP server with full REST and SSE APIs, enabling integration with web frontends, webhooks, and other services. See the REST API Documentation for available endpoints.

const agent = new DextoAgent(config);
await agent.start();
// Create and manage sessions
const session = await agent.createSession('user-123');
await agent.generate('Hello, how can you help me?', session.id);
// List and manage sessions
const sessions = await agent.listSessions();
const history = await agent.getSessionHistory('user-123');
await agent.deleteSession('user-123');
// Search across conversations
const results = await agent.searchMessages('bug fix', { limit: 10 });

// Get current configuration
const currentLLM = agent.getCurrentLLMConfig();
// Switch models (provider inferred automatically)
await agent.switchLLM({ model: 'gpt-5.2' });
await agent.switchLLM({ model: 'claude-sonnet-4-5-20250929' });
// Switch model for a specific session
await agent.switchLLM({ model: 'gpt-5.2' }, 'session-123');
// Get supported providers and models
const providers = agent.getSupportedProviders();
const models = agent.getSupportedModels();

import { MCPManager } from '@dexto/core';
const manager = new MCPManager();
// Connect to MCP servers
await manager.connectServer('filesystem', {
  type: 'stdio',
  command: 'npx',
  args: ['-y', '@modelcontextprotocol/server-filesystem', '.']
});
// Access tools, prompts, and resources
const tools = await manager.getAllTools();
const prompts = await manager.getAllPrompts();
const resources = await manager.getAllResources();
// Execute tools
const result = await manager.executeTool('readFile', { path: './README.md' });
await manager.disconnectAll();

# agents/production-agent.yml
storage:
  cache:
    type: redis
    url: $REDIS_URL
  database:
    type: postgres
    connectionString: $POSTGRES_CONNECTION_STRING
sessions:
  maxSessions: 1000
  sessionTTL: 86400000  # 24 hours

Agent Registry

Pre-built agents for common use cases:

# List available agents
dexto agents list
Install and run
dexto agents install coding-agent podcast-agent
dexto --agent coding-agent

Available: Coding, Podcast, Image Editor, Video (Sora), Database, GitHub, Triage (multi-agent), and more.

See the full Agent Registry.

Agent Configuration

Dexto treats each configuration as a unique agent allowing you to define and save combinations of LLMs, servers, storage options, etc. based on your needs for easy portability. Define agents in version-controlled YAML. Change the file, reload, and chat—state, memory, and tools update automatically.

# agents/production-agent.yml
llm:
  provider: anthropic
  model: claude-sonnet-4-5-20250929
  apiKey: $ANTHROPIC_API_KEY
mcpServers:
  filesystem:
    type: stdio
    command: npx
    args: ['-y', '@modelcontextprotocol/server-filesystem', '.']
systemPrompt: |
  You are a helpful assistant with filesystem access.
storage:
  cache:
    type: redis
    url: $REDIS_URL
  database:
    type: postgres
    connectionString: $POSTGRES_CONNECTION_STRING
permissions:
  mode: manual

LLM Providers

Switch between providers instantly—no code changes required.

Built-in Providers

| Provider | Models | Setup | |----------|--------|-------| | OpenAI | gpt-5.2, gpt-5.2-pro, gpt-5.2-codex, o4-mini | API key | | Anthropic | claude-sonnet-4-5-20250929, claude-opus-4-5-20250929, extended thinking | API key | | Google | gemini-3-pro, gemini-2.5-pro, gemini-2.5-flash | API key | | Groq | llama-4-scout, qwen-qwq, deepseek-r1-distill | API key | | xAI | grok-4, grok-3, grok-3-fast | API key | | Cohere | command-r-plus, command-r | API key |

Local Models (Privacy-First)

| Provider | Models | Setup | |----------|--------|-------| | Ollama | Llama, Qwen, Mistral, DeepSeek, etc. | Local install | | node-llama-cpp | Any GGUF model | Bundled (auto GPU detection: Metal, CUDA, Vulkan) |

Cloud Platforms

| Provider | Models | Setup | |----------|--------|-------| | AWS Bedrock | Claude, Llama, Mistral | AWS credentials | | Google Vertex AI | Gemini, Claude | GCP credentials |

Gateway Providers

| Provider | Access | Setup | |----------|--------|-------| | OpenRouter | 100+ models from multiple providers | API key | | LiteLLM | Unified API for any provider | Self-hosted or API key | | Glama | Multi-provider gateway | API key |

# Switch models via CLI
dexto -m claude-sonnet-4-5-20250929
dexto -m gemini-2.5-pro
dexto -m llama-4-scout

Switch within interactive CLI (/model) or Web UI without config changes.

See the Configuration Guide.

Demos & Examples

| Image Editor | MCP Store | Portable Agents | |:---:|:---:|:---:| | | | | | Face detection & annotation using OpenCV | Browse and add MCPs | Use agents in Cursor, Claude Code via MCP|

More Examples

Coding Agent

Build applications from natural language:

dexto --agent coding-agent
"Create a snake game and open it in the browser"

Podcast Agent

Generate multi-speaker audio content:

dexto --agent podcast-agent

Multi-Agent Triage

Coordinate specialized agents:

dexto --agent triage-agent

Memory System

Persistent context that shapes behavior:

Dynamic Forms

Agents generate forms for structured input:

Browser Automation

MCP Playground

Test tools before deploying:

Usage: dexto [options] [command] [prompt...]
Basic Usage:
  dexto                    Start web UI (default)
  dexto "query"            Run one-shot query
  dexto --mode cli         Interactive CLI
Session Management:
  dexto -c                 Continue last conversation
  dexto -r <id>            Resume specific session
Options:
  -a, --agent <path>       Agent config file or ID
  -m, --model <model>      LLM model to use
  --auto-approve           Skip tool confirmations
  --no-elicitation         Disable elicitation prompts
  --mode <mode>            web | cli | server | mcp
  --port <port>            Server port
Commands:
  setup                    Configure global preferences
  deploy                   Deploy current workspace to cloud
  agents install <agents...>  Install agents from registry
  agents list              List available agents
  session list|history     Manage sessions
  search <query>           Search conversation history

Documentation

• Quick Start – Get running in minutes
• Configuration Guide – Agents, LLMs, tools
• SDK Reference – Programmatic usage
• REST API – HTTP endpoints

Telemetry

We collect anonymous usage data (no personal/sensitive info) to help improve Dexto. This includes:

• Commands used
• Command execution time
• Error occurrences
• System information (OS, Node version)
• LLM Models used

Set env variable DEXTO_ANALYTICS_DISABLED=1

Contributing

See CONTRIBUTING.md.

Community

Built by Truffle AI. Join Discord for support.

If you find Dexto useful, please give us a ⭐ on GitHub—it helps a lot!

Elastic License 2.0. See LICENSE.