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 run AI agents across multiple devices (desktop, mobile, and browser). It solves the problem of fragmented AI workflows by allowing users to track tasks on a board and maintain isolated workspaces that serve as a knowledge base.

How it works

Agents run locally on the user's own devices, with each added machine acting as an additional node for the agents to work. The system uses isolated workspaces to keep work separate and build a knowledge base of documents. Users can convert conversations into tasks on a board, which evolve into purpose-built agents over time. The platform also provides an Open API with SSE and WebSocket support for integrating these agents into external apps and workflows.

Who it’s for

Individuals and businesses who want a self-hosted, cross-device AI agent management system that integrates with their own applications via API.

Highlights

  • Cross-Device Sync: Accessible from desktop, mobile (Android Beta), and browser.
  • Self-Hosted: Agents run on the user's own hardware.
  • Task Board: Converts conversations into trackable tasks.
  • Isolated Workspaces: Maintains separate knowledge bases for different projects.
  • Open API: Supports SSE and WebSocket for external integration.
  • Integrated Models: Includes support for DeepSeek Harness and TypeSafe AI's Jev model.

Related

  • Project
    jaylfc/taOS

    taOS is a self-hosted AI agent platform that turns spare hardware (laptops, Pis, gaming PCs, phones) into a private distributed compute cluster. It offers a full web desktop environment, framework-agnostic agents, a self-hosted memory system (taOSmd), and large app/model catalogs—all offline-first with cloud as an opt-in. It's beta software with some rough edges and untested install manifests.

  • Project
    CopilotKit/OpenBot

    OpenBot is an open‑source, self‑hosted platform that lets you run AI “coworker” agents inside your own infrastructure. Each Bot gets its own container with a browser and file workspace, all tool calls pass through a policy‑enforced gateway that logs every action. Built on Docker Compose, Bun, PostgreSQL and the AG‑UI protocol, it works with any LLM (OpenAI, Anthropic, Google, or self‑hosted) via CopilotKit Intelligence. Features include per‑Bot computers, CEL‑based access policies, human‑in‑the‑loop hand‑offs, component‑rich responses, audit trails, encrypted credentials, and scheduled routines. The repo is a template (MIT‑licensed, Alpha status) meant to be cloned and customized for enterprise AI assistants, RAG bots, or automated workflows.

  • Project
    n-WN/SubgroupX

    A multi-user agent platform that allows AI agents to execute tasks on private, non-publicly routable machines via an outbound connector or cloud sandboxes.

  • Project
    getpaseo/paseo

    An open-source agentic development environment that provides a unified interface for multiple AI coding agents across desktop, mobile, and CLI.