Sandbox
Sign in
@YaoApp/yao
Harnesses#Any agent#Coding#Product#Data

Self-hosted agent workspaces and task board

Yao is a self-hosted workspace and task system for agents. You add machines, keep each workspace isolated, and manage the work from one board across desktop, mobile, browser, or API.

7,921 stars•706 forks•Go•Updated 7d ago
Who it's for

Builders who want a shared place to run agents, separate work by workspace, and track tasks across devices.

What it delivers

You can keep agent work organized in one place instead of juggling separate tools on each device.

What it does

Workspace isolation

Each workspace stays separate while agents work across your computers.

Task board

Conversations can become tasks on a board, so you can track ongoing work instead of losing it in chat.

Cross-device access

You can use the system from desktop, mobile, browser, or API.

Open API

Expert and task agents expose SSE and WebSocket APIs for use in your own apps and workflows.

Self-hosted deployment

You run it on your own devices and infrastructure instead of relying on a hosted-only service.

DeepSeek harness integration

The README says DeepSeek Harness is integrated and can be used directly in the desktop app, Android app, or browser.

README

Yao Agents

✨ 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.

How it works

🏠 Homepage: https://yaoagents.com

📚 Docs: https://yaoagents.com/docs

🖥️ Yao Desktop: https://yaoagents.com/download

📱 Android (Beta): APK Download

⚡⚡⚡ DeepSeek Harness is now integrated — use it directly in the desktop app, Android, or browser, running across your devices.

This README was written with DeepSeek Harness in the Yao Agents Android app (beta) and published automatically.

How it works

Agents run on your own devices. Every machine you add is another place for them to work, all managed from one place.

Workspaces

Every workspace is isolated. Work stays separate, managed across all your computers, and accumulates into documents that become your knowledge base.

While working, agents can read what they need from any node.

Task Board

Say what you need in a conversation, and it becomes a task on your board.

Keep the conversation going, keep it running, and it improves with use, growing into an agent purpose-built for this kind of work.

Connect task agents to your apps, or share them with others.

Open API

Expert and task agents integrate into your own apps and workflows. They're built on standard APIs, with both SSE and WebSocket support.

Let your agents become part of your business, wherever you need them.

Links

Files in the repo

Repository payload•79 top-level entries
  • .github
  • agent
  • aigc
  • api
  • assert
  • attachment
  • audit
  • bin
  • cert
  • cmd
  • commercial
  • config
  • connector
  • crypto
  • cui
  • data
  • docker
  • docs
  • dsl
  • engine
  • event
  • excel
  • flow
  • fs
  • grpc
  • helper
  • i18n
  • importer
  • integrations
  • job
  • kb
  • llmprovider
  • mcp
  • mcpclient
  • messenger
  • model
  • monitor
  • openai
  • openapi
  • pack
  • pipe
  • plugin
  • query
  • registry
  • rss
  • runtime
  • sandbox
  • schedule
  • script
  • seed
  • service
  • setting
  • setup
  • share
  • sitemap
  • store
  • sui
  • tai
  • task
  • test
  • tools
  • trace
  • ui
  • unit-test
  • utils
  • wework
  • widget
  • widgets
  • workspace
  • yao
  • .gitignore
  • go.mod
  • go.sum
  • LICENSE
  • LICENSE.zh-CN
  • main.go
  • Makefile
  • README.md
  • README.zh-CN.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More harnesses

affaan-m/
ECC
affaan-m/ECCHarnesses

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

258k
ruvnet/rufloHarnesses

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

72k
cobusgreyling/loop-engineeringHarnesses

Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

11k