Skip to content
YuLab-SMUPublic

About

an agent-native desktop workbench for R

Resources

Contributing

Security policy

Stars

33 stars

Watchers

0 watching

Forks

Repository files navigation

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

Repository Responsibility
Rho-core Intelligent-system foundation: managed execution, request identity, retained execution facts and resident Host
Rho-plugins Reusable document/code, file/artifact, runtime/object, requirement, table, media/chart and Agent capabilities; optional reusable domain adapters
Rho Component selection and assembly, local service, workspace layout, shared interaction and presentation; native windows in a later client

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. Rho connects those components to the Core's public capabilities.

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 direction is an npm launcher and local service with React, TypeScript, Vite and Dockview. Electron is reserved for a later desktop client that reuses the WebUI and component boundaries. Initial functional views use CodeMirror 6, AG Grid Community and ECharts. Agent-composed interfaces use a typed json-render catalog; independent HTML views can use an isolated MCP Apps host when needed.

The versioned local backend, npm launcher, client and read-only state fixtures are implemented. Start the headless service or inspect its extraction acceptance. The browser shell and component views remain to be implemented; backend checks do not establish product release acceptance. Status records the current evidence and limits.

Start with the prioritized first-release tasks, Architecture, Technology stack and Roadmap. The documentation index covers product design, development and distribution. Contributions follow Contributing; source is licensed under AGPL-3.0.

About

an agent-native desktop workbench for R

Resources

Contributing

Security policy

Stars

33 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages