A frontend UI solution for the AI era, including UI protocols, rendering SDKs, and component libraries for Generative UI, AI Agents, and LLM applications.
cosui is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view baidu/cosui --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
COSUI is a set of tools for building user interfaces for AI-powered applications. It provides protocols (like Markdown and JSON) to define dynamic UIs, and SDKs to render them on mobile and web.
COSUI is a comprehensive frontend UI solution designed for AI applications. It includes: - **UI Protocols**: Data-driven rendering protocols (Markdown extension and JSON dynamic protocol) for structuring and displaying UI components. - **Rendering SDKs**: Complete SDKs for parsing and rendering Markdown extensions and JSON protocols. - **Component Library**: San-based UI components built on the Cosmic Design Token system. - **Multi-terminal Support**: Works on both mobile H5 and PC. - **Theme Customization**: Supports theme customization via design tokens. It is ideal for Generative UI, AI chatbots, and AI agent interfaces.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 48 days ago.
87 GitHub stars indicate community interest.
0 open issues signal maintenance load.
Apache-2.0 license detected.
Building dynamic, data-driven UIs for AI chatbots
Creating interactive UI components for AI agent outputs
Rendering generative UI from Markdown or JSON protocols
Developing multi-terminal frontends for LLM-powered applications
Standardizing UI component communication in AI systems
Ensure proper sanitization of user-provided Markdown/JSON to prevent XSS attacks.
Data-driven UI rendering may expose sensitive data if protocols are not secured.
Use HTTPS and validate input when integrating with external LLM services.
Review dependencies for vulnerabilities, as SDKs may execute dynamic content.
Create a dynamic UI component for an AI assistant using COSUI's JSON protocol to display a list of recommended items with images and interactive buttons.
87
Stars
6
Forks
0
Issues
Apache-2.0
License
Extract any website's complete design system with one command.
Argos is an open source visual testing platform that detects unintended UI changes to help teams maintain quality.
Generate design system documentation for UI components directly from your AI agent, rendering into Figma or portable .md files.
A frontend UI solution for the AI era, including UI protocols, rendering SDKs, and component libraries for Generative UI, AI Agents, and LLM applications.
Frontend developers building AI interfaces, AI/LLM application developers, UI/UX designers working on AI products
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Ensure proper sanitization of user-provided Markdown/JSON to prevent XSS attacks. Data-driven UI rendering may expose sensitive data if protocols are not secured.
Similar or complementary options to evaluate include design-extract, Argos, uSpec.
Jul 11, 2026
4 security/trust notes recorded.
Setup difficulty is 2/5.