# CopilotKit/OpenGenerativeUI

Open-Source Generative UI Framework

Repository: https://github.com/CopilotKit/OpenGenerativeUI
Canonical: https://ross.abutalabs.com/products/opengenerativeui
Homepage: https://opengenerativeui.copilotkit.ai/
Language: TypeScript
License: MIT
License Family: permissive
Topics: agent-native, agentic-ai, agents, ai-agents, ai-copilot, ai-visualization, assistant-chat-bots, copilot, generative-ui, javascript, llm, open-source, typescript, visualization, agentic-visualization
Last push: 2026-06-10T23:23:43+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 35, longevity 12
- inputs: {"age_days": 174, "days_push": 84, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1520, forks 201 (observed 2026-08-28T04:04:57.764237+00:00)

## What it is
An open-source framework and showcase for building generative UI, where an AI agent (CopilotKit + LangChain Deep Agents) generates interactive HTML/SVG components like charts, 3D scenes, and algorithm visualizations rendered in sandboxed iframes. It includes a Next.js frontend, a LangGraph agent service, and a self-hosted MCP server exposing design-system tools to MCP-compatible clients.

## Use cases
- generate interactive UI components with an LLM agent
- visualize algorithms like binary search or sorting with AI
- build AI-generated charts and dashboards
- create 3D animations from natural language prompts
- add a generative UI copilot to a Next.js app
- expose a design system to Claude Desktop via MCP

## When to choose
- you want AI agents to render rich interactive visual components instead of plain text
- you're building with CopilotKit or LangChain and need a generative UI reference implementation
- you need an MCP server that assembles styled HTML documents for AI clients

## When to avoid
- you need production UI generation with small or weak LLMs, which produce broken layouts
- you want a traditional static component library rather than AI-generated UI
- you can't run multiple services (frontend, agent, MCP server) locally

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, data-visualization, chatbot, mcp, ui-components
- domain: artificial-intelligence, large-language-models, data-visualization, web-development, frontend
- platform: self-hosted
- tags: generative-ui, copilotkit, langchain, langgraph, sandboxed-iframe, nextjs, anthropic-claude, agentic-ui, showcase-app, ai-agents, nodejs, typescript, web-server, docker

## Member repositories
- CopilotKit/OpenGenerativeUI (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:57.764237+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:31:53.424441+00:00, confidence not recorded.
  - readme: https://github.com/CopilotKit/OpenGenerativeUI (fetched 2026-08-28T04:04:57.764237+00:00, sha 0d7c4ecdaeea)
  - homepage: https://opengenerativeui.copilotkit.ai/ (fetched 2026-08-29T11:35:15.066348+00:00, sha 6506a5446232)
- Data as of 2026-08-30T08:39:29.467469+00:00.