AG-UI vs assistant-ui
Which should you use? A side-by-side look at what each one does, who it suits, what it costs, how hard it is to set up, and where each falls short.
Open source · MIT
An open protocol that standardizes how AI agents connect to user-facing apps.
Open source · MIT
A TypeScript/React library for building AI chat interfaces in your app.
The short answer
Choose AG-UI if you need…
- Developers adding an AI agent to a web or in-app user interface
- Teams using a supported agent framework such as LangChain, CrewAI, or Google ADK who want a standard frontend connection
- Builders who want real-time streaming chat and shared state between agent and UI
Choose assistant-ui if you need…
- React or Next.js developers adding an AI chat panel to an existing app
- Teams that want to style chat UI with their own design system or shadcn/ui
- Developers who need tool-call rendering or inline human approval in a chat
- Projects already using the Vercel AI SDK or LangGraph
Side-by-side
| AG-UI | assistant-ui | |
|---|---|---|
| Type | Framework | Library |
| Price | Free and open source | Free and open source |
| Licence | MIT | MIT |
| GitHub stars | 17k | 12.9k |
| Setup difficulty | Intermediate | Intermediate |
| How you get it | Install with a package manager | Install with a package manager |
| Main language | TypeScript | TypeScript |
| Last code update | 5 days ago | 4 days ago |
What each one is
AG-UI
AG-UI is an open, lightweight, event-based protocol that defines how AI agent backends send events to a user interface and accept simple inputs in return. The README says it works over any event transport such as SSE or WebSockets, and it ships with a reference HTTP implementation and a default connector. Developers use it to bring agents into frontend applications, such as chat, shared state, and human-in-the-loop workflows.
assistant-ui
assistant-ui is an open-source TypeScript and React library for building chat interfaces like ChatGPT inside your own web app. It provides composable chat pieces such as threads, messages, and a composer, and connects them to backends like the Vercel AI SDK, LangGraph, or your own custom backend.
Best for
AG-UI
- Developers adding an AI agent to a web or in-app user interface
- Teams using a supported agent framework such as LangChain, CrewAI, or Google ADK who want a standard frontend connection
- Builders who want real-time streaming chat and shared state between agent and UI
assistant-ui
- React or Next.js developers adding an AI chat panel to an existing app
- Teams that want to style chat UI with their own design system or shadcn/ui
- Developers who need tool-call rendering or inline human approval in a chat
- Projects already using the Vercel AI SDK or LangGraph
Strengths
AG-UI
- Built on a small set of about 16 standard event types, per the README
- Transport-flexible: the README says it works with SSE, WebSockets, webhooks, and others
- Has a broad list of supported frameworks and an MIT license
assistant-ui
- Composable primitives let you build custom chat layouts instead of using one fixed component
- Includes streaming, attachments, markdown, and accessibility features according to the README
- Typed TypeScript APIs for runtimes, tool schemas, and message parts
Not ideal for
AG-UI
- People who only want a ready-made chat product without writing code, since the README describes a protocol and developer tooling
- Projects that need tool access for agents alone, since the README positions MCP for that role rather than AG-UI
assistant-ui
- People who want a finished chat app without writing any code, since it is a library for developers
- Projects not using React, because the library is built for React and TypeScript
- Teams that need a single drop-in component with no customization, since the README describes composing primitives instead
Trade-offs
AG-UI
- The README is truncated and does not give full API details, so integration effort is hard to judge from it alone
- Several listed integrations are marked In Progress or rely on partner documentation hosted elsewhere
assistant-ui
- Requires React and TypeScript knowledge, so it is not beginner-friendly for non-developers
- The README is truncated and does not fully document every backend or setup detail
- Being a library, you still need to supply and pay for your own model provider and backend
Getting started
AG-UI
Create a new AG-UI application
npx create-ag-ui-app my-agent-appassistant-ui
Create a new project with the CLI
npx assistant-ui@latest createAdd to an existing project with the CLI
npx assistant-ui@latest initFrequently asked questions
What is the difference between AG-UI and assistant-ui?
AG-UI: An open protocol that standardizes how AI agents connect to user-facing apps. assistant-ui: A TypeScript/React library for building AI chat interfaces in your app. AG-UI suits developers adding an ai agent to a web or in-app user interface, while assistant-ui suits react or next.js developers adding an ai chat panel to an existing app.
Are AG-UI and assistant-ui free?
AG-UI: Free and open source. assistant-ui: Free and open source.
Is AG-UI or assistant-ui more popular?
AG-UI has more GitHub stars (17k) than assistant-ui (12.9k). Popularity isn't the same as fit — check which one matches your use case above.
What are other alternatives to AG-UI and assistant-ui?
Other options people compare them with include CopilotKit, shadcn/ui, Radix Primitives, Base UI.
Keep comparing
Built from our catalogue entries for both products: open-source details come from each project's README (AI-assisted, refreshed weekly) and GitHub data; AI-tool details are editorial. Spotted something wrong? Let us know from either product's page.