Rho

Rho

Rho is an application container for an intelligent, composable workspace. People and Agents use the same functional components to act on real resources, inspect results and arrange the tools they need.

The first release brings natural-language interaction, code/data/graphics and arranged views within one browser window into one workflow. It is distributed through npm and runs as a local service with a WebUI. An Agent can compose interfaces from registered components while the user continues editing and inspecting the same resources. Architecture Components may expose CLI, Skills, MCP and UI entries as their consumers require. They retain their implementation, conditions and results across headless and application use. Agents use native tools normally; Rho connects shared workspace capabilities and uses Core only for selected managed operations or activity observation.

A specific analysis workflow is project code or an acceptance example, not a plugin. The plugin extraction plan applies the capability model to the backend. Version 0.4 independently packages eight selected capabilities and keeps workflow actions and recipes outside those packages; an ordinary R project and the original analysis use the same declared execution, dependency, resource and selection contracts. Technology direction

The first release is an npm launcher and local service with a React, TypeScript and Vite WebUI. The workspace lays out the owners' views in Rho's own tabs and splits, arranged by the Agent and the person through one conditional layout contract. Electron is reserved for a later desktop client that reuses the WebUI and component boundaries. Functional views use CodeMirror 6, AG Grid Community and ECharts.

Install it with npm install -g @rho-workspace/rho on Node 22.22 or later, below 27, start rho, and connect an external Agent with rho --grant (Install and start). Projects, files, execution records and workspaces are available through the local WebUI. The Agent uses the same scoped capabilities; a browser request copied to an external Agent is explicitly a handoff.

The frontend was reconstructed on 2026-10-25 after withdrawing the earlier design plans and visual rules. See Frontend for the current interface, Status for executed checks and limits, and the documentation index for backend and release information. Set up with an Agent

A person can ask Claude Code or Codex, in any language: Read https://yulab-smu.top/Rho/doc/setup.md and follow its steps to install and configure Rho for me.

or: 请阅读 https://yulab-smu.top/Rho/doc/setup.md 文档，按照步骤为我安装并配置 Rho。

That page is SETUP.md. The Agent checks the machine, installs the npm package and starts Rho on ~/Rho/projects and ~/Rho/state. It then installs the Agent Skill in skills/rho into its own skills folder, connects itself to the example project and says what is missing. The Skill teaches an Agent to install and connect Rho, call its tools without guessing, and run an analysis a person can follow. It is published beside the page at . Documentation

runs the real interface on the shipped example project, replaying a recorded session without a backend, and gives the sentence above for an Agent. The documentation is published at . The site is generated from this repository's docs/ directory, which stays the only source of truth: every page names the file it came from and links to it.

@rho-workspace/rho is published to npm. The registry entry for 0.5.2 carries no README, so its package page shows no description; from 0.5.3 the packer ships this README.

For a new component view, start with Plugin authoring: generate a typed package, preview it independently and select its compiled entry through configuration without adding an application adapter.