#2929th of 42 in Agent platforms
yao
Self-hosted agent manager with isolated workspaces and a task board
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 8.2k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Go
7,454 on 1 Apr 20268,172 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Yao Agents runs agents on machines you own and manages them from one place, through a desktop app, Android beta, browser or API. Conversations become tasks on a kanban board, and each isolated workspace accumulates documents as a knowledge base. Agents are exposed through standard APIs with SSE and WebSocket support.
Who it is for: Self-hosters who want agents and tasks managed across their own devices
Strengths
- Runs agents across multiple devices you add, managed from one place
- Task board turns conversation requests into tracked tasks
- Isolated workspaces keep work separate and build up documents
- API access over SSE and WebSocket for embedding agents in your apps
Weaknesses
- README gives no install steps, hardware needs or supported model list
- License is not identified (NOASSERTION), so terms need manual checking
- Android client is labeled beta
- No Docker or compose files detected
What it needs
- Docker
- Models: DeepSeek Harness, Jev
Also in Agent platforms
See all 42| Rank | Project | Score |
|---|---|---|
| 1 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 81 out of 100 |
| 2 | daily_stock_analysisDaily LLM stock analysis for A-share, HK, US and other markets, pushed to chat apps | 81 out of 100 |
| 3 | resume-matcherTailors resumes and cover letters to job descriptions using local or hosted LLMs | 81 out of 100 |
| #4 | vibe-tradingFinance research agent for backtests, market data and broker connectors | 78 out of 100 |
| #5 | deer-flowAgent harness that runs sub-agents, memory and sandboxed skills for long tasks | 77 out of 100 |