Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Dodaios

Dodaios: A voice-driven assistant that directs your models, coding agents and computer.

What problem it solves

Dodaios provides a locally installed, open-source way to make a personal AI assistant the control center for work on your computer. Its lead assistant coordinates models, coding agents, and computer use, while chats, memory, documents, and settings remain files on the computer that runs Dodaios.

Key features

  • Voice, chat, and phone interaction — The lead assistant supports wake words, dictation, real-time spoken conversation, chat, and a paired phone. Phone calls are available as an early preview and require the user's own Twilio number.

    Source: README

  • Multiple model providers — The assistant is not tied to one provider and can work with Claude, OpenAI, Gemini, or local Ollama models.

    Source: README

  • Side-by-side coding agents — Coding agents run in a built-in Agentic IDE as Claude Code or Codex terminals, locally or on servers over SSH. Each agent has a name, with Git integration and task splitting also included.

    Source: README

  • Persistent agents and automation — Persistent named agents can message each other, while memory, standing tasks, workflows, skills, and opt-in life admin support longer-running work. The assistant can also create documents, slides, sheets, and dashboards.

    Source: README

Quick start

Copied verbatim from the project's README.

curl -fsSL https://raw.githubusercontent.com/Dodaios/Dodaios/main/install/install.sh | bash
irm https://raw.githubusercontent.com/Dodaios/Dodaios/main/install/install.ps1 | iex
dodaios            # start the desktop app
dodaios update     # install the newest release

Who it may suit

Inference: Dodaios may suit developers and desktop users who want voice-driven AI assistance alongside coding agents, and it may also suit teams running browser-based instances on servers without a display.

Topics to discuss

  • Which coding-agent workflows should be prioritized in the built-in Agentic IDE?

  • How should persistent named agents divide work and communicate with the lead assistant?

  • Which approval boundaries and asking modes best balance automation and user control?


Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/Dodaios/Dodaios#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/Dodaios/Dodaios

Comments

…