tutti-os/tutti

Where people and agents build in tune.

What it solves

Tutti addresses the "messenger problem" where users must manually copy-paste context, files, and requirements between different AI agents (like Claude Code and Codex) and separate apps. It eliminates the friction of re-explaining project state to every new agent or tool in a workflow.

How it works

Tutti provides a real-time shared workspace that connects context, files, and tasks across multiple agents. It allows agents to share a "single brain" where one agent can reference the output or conversation history of another using a "Big @" system. It also includes an app ecosystem (for image generation, UI/UX design, etc.) that both users and agents can invoke directly within the workspace, using the user's existing agent subscriptions.

Who it’s for

  • Independent developers who use multiple coding agents for different stages of a project.
  • Designers and Product Managers who want to move from PRDs to prototypes and code without leaving the environment.
  • Content creators managing end-to-end production of scripts and visuals.
  • Teams (via Tutti · VM) who need multi-user, multi-agent collaboration across different devices.

Highlights

  • Big @ Reference: Mention past conversations, files, or other agents to transfer context instantly.
  • Integrated App Center: Built-in tools for design, PPTs, and docs that agents can call as capabilities.
  • Goal-to-Task Orchestration: Automatically breaks high-level goals into sub-tasks for assignment to specific agents.
  • Subscription Reuse: Connects to existing subscriptions (e.g., Claude Code, Codex) rather than requiring a new one.
  • Control Center: A centralized GUI to manage all running tasks and agent approvals without switching tabs.

Related

  • Project
    openteams-lab/openteams

    A local-first AI desktop app that provides a shared workspace for multiple coding agents to collaborate, plan, and execute tasks without interfering with each other.

  • Project
    openagents-org/openagents

    An open-source collaborative OS for AI agents that provides a unified workspace where multiple agents can share threads, files, and a browser to work together.

  • Project
    LodyAI/Lody

    A shared workspace for team collaboration with coding agents, allowing teams to dispatch work and track agent progress across desktop, mobile, and CLI.

  • Project
    xintaofei/codeg

    A multi-agent coding workspace that aggregates various AI coding agents into one searchable interface, enabling multi-agent collaboration and unattended task execution via Git worktrees.

  • Project
    Team-Commonly/commonly

    An open-source workspace for collaborating with AI agents from any runtime, providing them with persistent identity and shared project memory to eliminate redundant context-setting.