The harness
Run agents on your machine with the Dexto CLI, using Dexto models or your own provider keys, with skills, MCP servers, and plugins.The harness is the part of dexto that runs an agent on your computer: it talks to a model,
calls tools, keeps chat history, and asks you before anything risky. It works signed out, with
your own model provider keys, and gets more when you sign in.
dexto # chat in your terminaldexto --prompt "review this diff" # start the chat with a promptdexto --continue # resume the most recent chatdexto --resume <session-id> # resume a chat by iddexto --agent ./my-agent.yml # use an agent from a filedexto --mode web # the web UIThe first time you run it, dexto setup picks a provider and model. Run it again to change them.
dexto connect connects a provider’s sign-in or key. Both have --no-interactive forms for scripts:
dexto setup --provider anthropic --model claude-sonnet-5-5 --no-interactivedexto connect --provider <provider> --method <method> --no-interactiveRun one prompt
Section titled “Run one prompt”dexto run "summarize this repository"echo "fix lint errors" | dexto rundexto run needs no terminal. It prints JSON when stdout is not a terminal, and the reply at one.
Approvals nobody can give are refused and listed in the result, so a headless run never hangs on a
question. See dexto run for the result and --stream-json events, and
the reference for its options.
To let an agent run its tools without asking, use --auto-approve (or --permissions-mode auto-approve). Mandatory approvals still apply.
Models
Section titled “Models”- Your own key:
dexto setupordexto connectfor a provider such as Anthropic, OpenAI or Google. You pay the provider. - Dexto models: signed in, models shown as
dexto/<model>run on your sign-in and bill your organization’s credits in the current Cloud project.dexto models listshows them anddexto billingshows your balance. Spending credits asks for a permission the first time.
Pick a model with -m, --model for one run, or in the agent’s file.
The Dexto MCP
Section titled “The Dexto MCP”Signed in, every local session gets a server called dexto with your connectors, Drive, Sites and
Apps, Loops and memory. The same tools are available from the terminal with
dexto workspace.
Your own MCP servers
Section titled “Your own MCP servers”dexto mcp add github --command npx --arg=-y --arg @modelcontextprotocol/server-githubdexto mcp listdexto mcp tools githubdexto mcp call github <tool> …dexto mcp also configures an aggregation server. See MCP commands.
Agents, skills and plugins
Section titled “Agents, skills and plugins”dexto agents list # installed and available agentsdexto agents install coding-agentdexto plugin marketplace add owner/repodexto plugin install ./my-plugindexto init # make this folder a Dexto workspacedexto skills push ./my-skill # add a skill folder to your librarySee Local agents and plugins and Setup and workspace folders.
Chat history
Section titled “Chat history”dexto chat listdexto chat history <id>dexto search "invoice"dexto chat local # Claude Code and Codex chats on this machinedexto chat import … # bring them into DextoAn imported chat keeps which model answered each turn, and the answer shows it under More. When you
continue the chat in Dexto, it uses the model of its last answer if your account can use it.
Otherwise it uses your default model and says so. To continue Codex chats on your ChatGPT plan, run
dexto connect codex first, or connect it later and import the chats again. See
Continue imported chats on their model.