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. observed · 2026-08-28
Health v2 · maintenance only
99/100
- Activity 99
- Release rhythm 99
- Longevity 100
Flags: no_license
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: 1
- age_days: 1822
- days_rel: 11
- days_push: 11
- n_releases_24m: 58
Adoption not part of the score
7812 stars · 696 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
Yao Agents is a self-hosted, AI-native platform for running AI agents and workspaces across your own devices, with a task board, isolated workspaces, and an open API (SSE/WebSocket). It integrates a DeepSeek Harness, supports MCP/skills/hooks extensibility, and runs as a single-binary engine on desktop, mobile, browser, or server.
Use cases
- run ai agents on my own devices self-hosted
- orchestrate coding agents across multiple machines
- turn conversations into tasks on a kanban board handled by agents
- schedule autonomous ai agents to process emails and data 24/7
- integrate ai agents into my apps via api with sse and websocket
- build a private knowledge base from agent work outputs
- extend agents with mcp tools and skills
- keep ai agent data local instead of a third-party cloud
When to choose
- you want self-hosted, local-first agent orchestration with data on your own machines
- you need agents running concurrently across multiple computers or servers from one console
- you want a task-board workflow where agents mature into purpose-built assistants
- you need MCP, hooks, and skills extensibility with an open API for embedding agents in apps
When to avoid
- you only need a simple chatbot UI without multi-device orchestration
- you require a fully permissive license - the license is Apache 2.0 modified (NOASSERTION)
- you want a managed cloud service rather than running your own engine
- you need heavy vision/audio model support with DeepSeek only, since DeepSeek lacks vision and audio slots
Facets
application · maturity active
agent-framework mcp chat-interface workflow-automation scheduling webhook self-hosted api-framework artificial-intelligence large-language-models self-hosted developer-tools self-hosted cross-platform windows go agent-orchestration agent-workspaces task-board local-first coding-agent deepseek-harness claude-code-ecosystem no-code own-your-data open-api ai-agents automation desktop web-server docker linux macos android ios
5 sources
- readme: https://github.com/YaoApp/yao · fetched 2026-08-28 · 649a2df2e972
- homepage: https://yaoagents.com · fetched 2026-08-29 · e54223552885
- site_page: https://yaoagents.com/features · fetched 2026-08-29 · f5fe92f06218
- site_page: https://yaoagents.com/docs · fetched 2026-08-29 · 60634f1d03e6
- site_page: https://yaoagents.com/docs/en-us/getting-started/installation · fetched 2026-08-29 · 67db137e3d52
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| YaoApp/yao | main | 99 |
For agents
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem