@assistant-ui

Stacked headings that reveal or hide content sections.

Floating chat bubble for support widgets and help desks.

Small label for status, categories, and metadata.

Token usage against a model's context window as a ring, bar, or text, with a hover popover.

Render mention directives as inline chips in user messages.

Who you are about to talk to: its skills, its model, and the endpoint behind it.

One pill that always answers: what is it doing, and for how long.

Work still going somewhere else, and the results waiting to be collected.

The whole family working together: a message, a pause, a streamed reply.

A snippet with a run button, and the output it produced attached below it.

The unified input: attachments, commands, mentions, models, voice, and context in one surface.

The socket drops, the run keeps going on the server, and the stream is picked back up.

Find inside a long thread, with every hit marked down the scrollbar.

Chronology in a long thread: days marked, times on hover.

A document the answer leans on, with the quoted passage and the page to jump to.

A server pausing mid-tool-call to ask you for the fields it still needs.

Next.js route handler that streams chat completions through the AI SDK.

Side panel chat for copilot experiences and inline assistance.

Assistant page wired to the AI SDK chat route, with the thread component installed.

Render code diffs with highlighted additions and deletions.

5x5 dot matrix indicator with state specific blink patterns.

Control passing between agents, with the reason and what came along.

Human in the loop: the agent asks before it runs anything with side effects.

The thread steps aside and the document takes the room, still being written as you read.

Points you can fall back to, with what each one would give back.

Everything the app can do, one keystroke away and grouped by where it acts.

The screen the agent is driving, with a cursor trail and what it is doing right now.

Where the window actually went: prompt, tools, files, conversation, and what's left.

What the run spent, split by model, against the session total.

A drawn answer with zoom, reset, and a full-bleed view; you hand it the rendered graphic.

Come back to a thread and the sentence you never sent is still waiting.

The first screen: a greeting, three ways in, and the composer front and center.

AI SDK route handlers with resumable stream context, so a run survives a reload.

Attach files from the composer and view them inside messages.

Character triggered picker for @ mentions, / commands, and similar popovers.

Direction provider and hook for right to left layouts.

A half-year of runs as a calendar of cells, dense where the work was.

A checklist the agent works through, with progress you can glance.

A generated document as a tangible object, written live and versioned.

Area, line, and bars, with points landing one at a time as the series streams in.

A unified diff with tinted additions and removals, sized for chat.

Two options weighed side by side, with the pick named and argued.

Which claims came from a source, which were inferred, and which are guesses.

The props-driven context usage display: ring, bar, and text presets with the usage popover, no runtime required.

A small comparison table the model can answer with directly.

The props-driven directive chip renderer: bring your own formatter, no runtime required.

Rewrite a turn in place, told up front how many replies the edit throws away.

A quiet failure banner with a retry path, not a modal in your face.