BoardUI/boardui

React design system for agentic interfaces. Every free BoardUI component as source, with a working AI chat app on your own model key as the homepage.

What it solves

BoardUI provides a specialized React design system tailored for building AI agent interfaces. It bridges the gap between standard dashboard components (like tables and charts) and AI-specific UI elements (like thinking indicators and agent logs), providing a unified visual language for AI products.

How it works

Unlike traditional component libraries that are installed as dependencies, BoardUI provides components as source files that are copied directly into a project using a CLI (npx boardui add). It is built on top of React Aria Components and Tailwind CSS v4, ensuring accessibility and no runtime CSS. It also includes an MCP server, allowing AI coding agents (like Claude Code or Cursor) to browse the catalog and install components automatically.

Who it’s for

Frontend developers and AI product builders who need a professional, accessible, and customizable design system specifically designed for agentic workflows and AI dashboards.

Highlights

  • Agent-Native Components: Includes specialized blocks like Agent Chat, Agent Log, and Agent Thinking indicators.
  • Sourced-Based Distribution: Components are added as source files, allowing full developer control and customization.
  • AI-Agent Integration: Features an MCP server and specific agent rules (AGENTS.md) to help AI coding tools build with the system.
  • Broad Provider Support: Includes a streaming chat runtime that supports multiple providers including OpenAI, Anthropic, Google, OpenRouter, Groq, and xAI.
  • Comprehensive Library: Offers over 60 free components ranging from base building blocks to complex application blocks.

Related

  • Project
    tweag/monad-bayes

    A Haskell library for probabilistic programming that enables the modular composition of Bayesian inference algorithms.

  • Project
    tensorflow/tflite-support

    A toolkit for developing and deploying TFLite models to mobile devices, providing tools for metadata management, automatic API generation, and optimized task libraries.

  • Project
    astronomer/agents

    AI agent tooling for data engineering that extends AI coding agents with specialized skills and an MCP server for managing Apache Airflow and querying data warehouses.

  • Project
    chi2liu/ABC-GRPO

    An asymmetric and adaptive refinement of the GRPO reinforcement learning algorithm that uses four independent clipping boundaries to prevent entropy collapse and improve generalization in LLM reasoning tasks.