YaoApp/yao

✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.

What it solves

Yao Agents provides a centralized, self-hosted platform to manage and deploy AI agents across multiple devices (desktop, mobile, and browser) from a single interface. It solves the problem of fragmented agent management by allowing users to track tasks on a board and maintain isolated workspaces for different projects.

How it works

Agents are deployed locally on the user's own devices, with each added machine serving as a node for the agents to work. The system uses isolated workspaces to keep work separate and build a knowledge base of documents. Users can create tasks via conversation, which are then tracked on a task board, and agents can be integrated into external apps via a standard Open API supporting SSE and WebSocket.

Who it’s for

Individuals and businesses who want self-hosted AI agent management across multiple devices and the ability to integrate agents into their own custom workflows and applications.

Highlights

  • own-device execution: Agents run on your own hardware for better control.
  • Cross-platform access: Available via desktop app, Android (beta), and browser.
  • Task-driven workflow: Converts conversations into trackable tasks on a board.
  • Open API: Supports SSE and WebSocket for integration into business apps.
  • DeepSeek Harness integration: Integrated directly into the desktop, Android, and browser apps.

Related

  • Project
    hezo-ai/hezo

    A self-hosted server and web app for running sandboxed teams of AI agents organized as a corporate hierarchy with built-in budget caps and secure secret management.

  • Project
    jaylfc/taOS

    A self-hosted AI agent platform that turns spare hardware into a distributed compute cluster, providing a framework-agnostic memory system and a full web-based desktop interface.

  • 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
    micro/mu

    A self-hosted runtime for AI agents and services that allows users to run their own personal assistant, tools, and contextual memory in a single binary.

  • Project
    777genius/agent-teams-ai

    A desktop orchestration layer for AI agent teams that allows users to coordinate multiple autonomous agents from different providers to handle coding and project tasks via a Kanban board.