assistant-ui
Skill44 starsChanged 3 months agoMITView on GitHub
Overview and router for assistant-ui, the React library for building AI chat interfaces from composable primitives. Use for high-level, cross-cutting, or architecture-overview questions: choosing packages, picking a runtime, or understanding the layered model (RuntimeCore, Runtime, context hooks, primitives) and message model. Covers the `@assistant-ui/react` core plus `@assistant-ui/react-ai-sdk`, `@assistant-ui/react-langgraph`, `assistant-stream`, and `assistant-cloud`; `AssistantRuntimeProvider`; the primitives `ThreadPrimitive`, `MessagePrimitive`, `ComposerPrimitive`; the hooks `useAui`, `useAuiState`, `useAuiEvent`; and runtime selection across `useChatRuntime`, `useExternalStoreRuntime`, `useLangGraphRuntime`, `useLocalRuntime`. For a specific area route to a focused sibling instead: setup, runtime, primitives, tools, streaming, cloud, thread-list, or update. Not for hands-on tasks already owned by those siblings.
4 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- YardonYan/ui-design-skillstheir own version, first seen Nov 15, 2026
- anthropics/claude-quickstartstheir own version, first seen Oct 13, 2026
- utopusc/livinity-ioedited, first seen Oct 8, 2026
- LucasMatuszewski/claude-code-course-jsystems-2026-07edited, first seen Jul 10, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- utopusc/livinity-io★ 7289% same
- LucasMatuszewski/claude-code-course-jsystems-2026-07★ 089% same
Wrote their own version · 2
- anthropics/claude-quickstarts★ 19ksame name
- YardonYan/ui-design-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- changelog-watchSkill
- claude-protocol-debuggerSkill
- codex-protocol-debuggerSkill
- mainframe-design-systemSkill
- radix-ui-design-systemSkill
- release-downloadsSkill
- shadcnSkill
- tauri-v2Skill
The file
Files
assistant-ui
Always consult assistant-ui.com/llms.txt for the latest API.
React library for building AI chat interfaces with composable primitives.
References
- ./references/architecture.md -- Core architecture and layered system
- ./references/packages.md -- Package overview and selection guide
When to Use
| Use Case | Best For |
| Chat UI from scratch | Full control over UX |
| Existing AI backend | Connects to any streaming backend |
| Custom message types | Tools, images, files, custom parts |
| Multi-thread apps | Built-in thread list management |
| Production apps | Cloud persistence, auth, analytics |
Architecture
┌─────────────────────────────────────────────────────────┐
│ UI Components (Primitives) │
│ ThreadPrimitive, MessagePrimitive, ComposerPrimitive │
└─────────────────────────┬───────────────────────────────┘
│
┌─────────────────────────▼───────────────────────────────┐
│ Context Hooks │
│ useAui, useAuiState, useAuiEvent │
└─────────────────────────┬───────────────────────────────┘
│
┌─────────────────────────▼───────────────────────────────┐
│ Runtime Layer │
│ AssistantRuntime → ThreadRuntime → MessageRuntime │
└─────────────────────────┬───────────────────────────────┘
│
┌─────────────────────────▼───────────────────────────────┐
│ Adapters/Backend │
│ AI SDK · LangGraph · Custom · Cloud Persistence │
└─────────────────────────────────────────────────────────┘Pick a Runtime
Using AI SDK?
├─ Yes → useChatRuntime (recommended)
└─ No
├─ External state (Redux/Zustand)? → useExternalStoreRuntime
├─ LangGraph agent? → useLangGraphRuntime
├─ AG-UI protocol? → useAgUiRuntime
├─ A2A protocol? → useA2ARuntime
└─ Custom API → useLocalRuntimeCore Packages
| Package | Purpose |
@assistant-ui/react | UI primitives & hooks |
@assistant-ui/react-ai-sdk | Vercel AI SDK v6 adapter |
@assistant-ui/react-langgraph | LangGraph adapter |
@assistant-ui/react-markdown | Markdown rendering |
assistant-stream | Streaming protocol |
assistant-cloud | Cloud persistence |
Quick Start
import { AssistantRuntimeProvider } from "@assistant-ui/react";
import { Thread } from "@/components/assistant-ui/thread";
import { useChatRuntime, AssistantChatTransport } from "@assistant-ui/react-ai-sdk";
function App() {
const runtime = useChatRuntime({
transport: new AssistantChatTransport({ api: "/api/chat" }),
});
return (
<AssistantRuntimeProvider runtime={runtime}>
<Thread />
</AssistantRuntimeProvider>
);
}State Access
import { useAui, useAuiState } from "@assistant-ui/react";
const api = useAui();
api.thread().append({ role: "user", content: [{ type: "text", text: "Hi" }] });
api.thread().cancelRun();
const messages = useAuiState(s => s.thread.messages);
const isRunning = useAuiState(s => s.thread.isRunning);Related Skills
/setup- Installation and configuration/primitives- UI component customization/runtime- State management deep dive/tools- Tool registration and UI/streaming- Streaming protocols/cloud- Persistence and auth/thread-list- Multi-thread management/update- Version updates and migrations
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

