What is Yao Agents and who makes it?

A self-hosted platform from YaoApp that puts all your agents and workspaces in one place: a task board accessible from desktop, mobile, browser, or API, with each machine you add becoming another place agents can work.

How does Yao Agents use Jev?

Its README says Jev is TypeSafe AI's System One model and describes it as returning typed decisions with confidence rather than text, with a "Now available in Yao Agents" line linking to a release post on yaoagents.com. The digest does not show the API calls behind it.

How do I install or run Yao Agents?

The README points to yaoagents.com for the homepage and docs, yaoagents.com/download for the desktop app, and a download link for an Android beta. The digest excerpt does not include install commands or server requirements.

Is Yao Agents free, and what license does it use?

GitHub lists the repo license as NOASSERTION, meaning no standard license was detected. The README describes the product as self-hosted but states no pricing; check the site before assuming terms.

What does the Yao Agents Open API offer?

The README says expert and task agents integrate into your own apps and workflows through standard APIs with both SSE and WebSocket support, so agents can become part of your business processes.

How do workspaces and the task board differ?

The task board turns what you say in a conversation into tasks, while workspaces isolate work across all your computers and accumulate into documents that become your knowledge base; agents can read what they need from any node while working.

How active is the Yao project?

GitHub metadata in the digest shows 8,134 stars, 723 forks, creation on 2021-09-06, and a push on 2026-10-16, the day before this entry. Go is the primary language.

Jev directory

CommunityJev Agents & MCP

Yao Agents

Self-hosted agent workspace platform from YaoApp that keeps all your agents and workspaces in one place across desktop, mobile, browser, or API, with Jev available inside it as TypeSafe AI's System One model for typed decisions with confidence.

See highlights Open github.com

Stars: 8.1k
Language: Go
Reading time: 2 min
Published by: Community
Author: YaoApp
Last verified: Oct 2026

yaoapp/yao

Organization repository on GitHub

View on GitHub

✨ 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.

Forks: 724
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

Tagscommunity github agents self-hosted go

Works forJev for Tool calling Jev for Realtime control

Used inJev for Software & DevTools

Languages: Go
Platforms: API Browser
Capabilities: Open sourceSelf-hosted

Highlights

README: "Jev is TypeSafe AI's System One model: it doesn't write text, it returns typed decisions with confidence."
Agents run on your own devices; every machine you add is another place for them to work, all managed from one place.
Conversations become tasks on a board; workspaces stay isolated and accumulate into documents that become your knowledge base.
Open API builds on standard APIs with SSE and WebSocket support; desktop app and Android beta via yaoagents.com/download.
GitHub metadata: 8,134 stars, 723 forks, Go, created 2021-09-06, last pushed 2026-10-16, license field NOASSERTION.

Watch out

README and GitHub metadata reviewed 2026-10-17. The digest excerpt names Jev and links a release post from 2026, but shows no endpoint, pricing, or model version, no install steps for the self-hosted server, and no details on the NOASSERTION license.

Questions about this entry

Short answers drawn from the linked project or page.

From the Jev guides

Original write-ups on what this entry is for.

MCP tool routing: Jev in front of the tool call

Oct 16, 2026

Tool menus can outgrow the context that reads them. The catalog's Jev-based routers and gates narrow the list: benchmarked tool search, per-tool scoring, fail-closed approvals, and WebMCP in the browser.

Jev Agents & MCP#mcp#tool-routing#agents

Read article

Approval policies for coding agents: hooks, guards, and gateways