Message
Composable conversation primitives for message rows, grouped bubbles, avatars, metadata, live markers, and a mount-only trailing-edge pop-up for newly sent rows.
Copy-paste AI agent components built with Motion and Tailwind CSS. Free, open source, and fully customizable.
Agent UI
Composable conversation primitives for message rows, grouped bubbles, avatars, metadata, live markers, and a mount-only trailing-edge pop-up for newly sent rows.
An auto-growing agent composer with prompt actions, model selection, keyboard submission, and animated send and stop states.
A stable response surface with completion actions, rendered content, and an expandable source summary.
One adaptive activity stream for reasoning, searches, tool calls, structured execution traces, or a chronological mix.
A lightweight execution disclosure for syntax-highlighted terminal output and request responses that collapses into a compact completed state.
A syntax-highlighted code surface with stable streaming updates, line numbers, focused lines, smooth following, and copy feedback.
A human-in-the-loop decision surface for approvals, single or multiple-choice questions, custom responses, and multi-step review flows.
A collapsible agent task plan with morphing status marks, a completion count, compact metadata, and smooth list updates.
A syntax-highlighted file change disclosure with progressive rows, line numbers, live change counts, smooth following, and completion collapse.
Inline citation markers paired with a collapsible, progressively rendered reference collection for grounded agent responses.
A stable generated-image surface that moves from queued work through progressive refinement to a completed result without layout shift.
A reader-aware conversation viewport that follows streamed output at the live edge and releases control when the reader moves away.
Example feedback
The motion feels considered without getting in the way.
The activity states make long-running work easy to follow.
I could drop these into a production chat without rebuilding the interaction layer.
The components are polished, readable, and easy to adapt.
The interface stays clear even while a run is still moving.
The small transitions make the whole workspace feel alive.
This is a calm starting point for an AI product surface.
The spacing, states, and feedback all feel like part of one system.
The source is easy to understand and the motion is easy to tune.
The previews answer the important question before I install anything.
The patterns feel ready to compose, not just ready to demo.
A thoughtful base for building a focused agent workspace.
The interaction patterns are crisp without feeling over-designed.
Streaming and tool states share the same clear visual language.
The best part is how much of the behavior is already considered.
Clean enough for a first screen, flexible enough for a full workspace.
Build with AgentUI
Compose polished agent interfaces with copy-paste components built for React and Next.js.