Agent Configuration

Agent Configuration

Your agent's behavior is controlled by two files:

  • .agent_instructions.md — personality, tone, rules (the agent's soul)
  • .mutiro-agent.yaml — technical config: model, tools, voice, workspace

The Config File

mutiro agents create generates .mutiro-agent.yaml automatically. You adjust it to fit your needs.

LLM Provider and Model

agent: genie: llm_provider: "genai" # genai | anthropic | openai | ollama | lmstudio model_name: "gemini-3-flash-preview" temperature: 0.7 # 0 = deterministic, 1 = creative max_tokens: 8000 # max response length

Workspace

Where the agent reads and writes files:

  • workspace: "." — personal agent, files stay in the agent directory
  • workspace: "./${USERNAME}" — shared agent, each user gets an isolated folder (default)

Voice

Enable text-to-speech responses:

agent: tts_voice: "en-US-Chirp3-HD-Orus" language: "en-US"

The language setting controls voice synthesis and audio transcription. The agent can text in any language regardless of this setting.

Available voice presets:

Voice ID Description
en-US-Chirp3-HD-Orus Male, warm (English US)
en-US-Chirp3-HD-Zephyr Female, clear (English US)
en-US-Chirp3-HD-Pulcherrima Female, expressive (English US)
pt-BR-Chirp3-HD-Callirrhoe Female (Portuguese BR)
en-GB-Chirp3-HD-Gacrux Female (English UK)

Full voice catalog: https://cloud.google.com/text-to-speech/docs/chirp3-hd

Tools

Tools define what the agent can do. If you omit the tools: section, the agent gets all default-enabled tools. When you specify tools explicitly, it's a complete override — list everything you want.

agent: genie: tools: - name: readFile - name: send_message - name: web_search # list every tool you want enabled

Tool Catalog

These are the exact name values to use in the config:

Workspace (file operations)

Tool Description Default
listFiles List files and directories in the workspace Yes
findFiles Find files by name or path pattern Yes
readFile Read a file from the workspace Yes
writeFile Create or update a file in the workspace Yes
searchInFiles Search file contents across the workspace Yes
viewImage Open an image for inspection No
viewDocument Open a document for inspection No

Messaging

Tool Description Default
send_message Send a text message Yes
send_voice_message Send a text-to-speech voice message Yes
send_image_message Generate and send an image Yes
edit_image_message Edit an image and send the result Yes
send_file_message Upload and send a file Yes
send_card Send an interactive card No
react_to_message Add an emoji reaction Yes
forward_message Forward a message to another conversation Yes

Memory and Recall

Tool Description Default
recall Semantically search conversation history Yes
recall_get Open a recalled item from history Yes
memory_get Read long-term memory Yes
memory_write Save to long-term memory Yes
working_memory_get Read current working memory snapshot No
working_memory_update Update current working memory snapshot No

Web

Tool Description Default
web_search Search the web, return summarized results No
web_fetch Fetch and extract content from a URL No

Scheduler

Tool Description Default
schedule_prompt_create Schedule a prompt to run later Yes
schedule_prompt_list List scheduled prompts Yes
schedule_prompt_cancel Cancel a scheduled prompt Yes

Planning

Tool Description Default
thinking Record private reasoning notes No
Skill Use a reusable skill Yes
TodoWrite Track task checklist No
Task Delegate to a helper agent No

Dangerous (owner-only, off by default)

Tool Description
bash Run shell commands in the workspace
process Inspect or control running processes
install_skill Install a reusable skill package
code Spawn an external coding agent (Claude Code, Codex)

Dangerous tools bypass every containment layer. See sharing and security for the security implications of tool choices.

Tool Selection Guide

  • Minimal agent (Q&A bot): omit tools: entirely, defaults are fine
  • Research agent: defaults + web_search, web_fetch
  • Deep thinker: defaults + thinking, TodoWrite, Task
  • Engineering manager: code, readFile, writeFile, thinking, Task, memory_get, memory_write

See agent recipes for full examples with personality sketches.

Live Calling

Enable real-time voice calls with the agent:

agent: live_calling_enabled: true

When enabled, users can initiate voice calls from the mobile or desktop app. The agent speaks and listens in real time.

Applying Changes

After editing either file, restart the agent:

mutiro start

Useful Commands

mutiro agents list # see all your agents mutiro agents get # agent details mutiro agents update-profile # change display name or bio mutiro agents regenerate-key # new API key mutiro agents delete # delete an agent mutiro agent doctor # diagnose issues