A shape-shifting AI input capsule that morphs between text, voice, thinking, and streaming states.
A shape-shifting AI input capsule that morphs between text, voice, thinking, and streaming states.
A model-effort picker: a stepped slider whose thumb is pulled toward the nearest level and springs onto it, with a cross-fading level name, a recommended mark and a pixel field that lights the track at the top level.
ElevenLabs AI voice platform logo with icon and wordmark variants
Static open-state emoji picker inline above a message with a recents row, category grid, search input, and existing reaction chips.
One page for a small independent estate agent (Carron Property, Stonehaven, Aberdeenshire). It leads with a free valuation, then the selling fee in plain figures, the steps from valuation to keys, a few current listings, the local team, and how to reach the office.
Eval pass rates per release as a shadcn line chart, including the regression we published.
A candidate prompt against the one in production: Run evals fills the grid cell by cell while the pass rate rolls, a regression opens both replies side by side with the failing part marked, and Ship waits until each one is decided.
Eve agent that turns a domain into a self-contained DESIGN.md — gathering the styleguide, screenshot, and homepage Markdown from context.dev, then composing the document in a single Claude call with the screenshot as a vision image.
Flue workflow that turns a domain into a self-contained DESIGN.md — gathering the styleguide, screenshot, and homepage Markdown from context.dev, then composing the document in a single Claude call with the screenshot as a vision image.
LangGraph agent that turns a domain into a self-contained DESIGN.md — gathering the styleguide, screenshot, and homepage Markdown from context.dev, then composing the document in a single Claude call with the screenshot as a vision image.
Mastra agent that turns a domain into a self-contained DESIGN.md — gathering the styleguide, screenshot, and homepage Markdown from context.dev, then composing the document in a single Claude call with the screenshot as a vision image.
Chat-style FAQ thread with question bubbles and assistant answers, ending with a chat CTA.
A feature section styled as a chat thread, pairing message bubbles with copy. Built to show a messaging or support product talking in real conversation.
AI response feedback row with thumbs up and down, a copy and regenerate action, and a reason picker revealed on negative feedback.
Prompt box built as a felt letter board: each key pushes a plastic letter into the groovesand Enter sets a homepage. Free React and HTML code.
Attached files, extraction status, and findings that cite the page or cell they came from.
Job list with status filters, live training progress and loss sparklines, a detail panel with an animated loss curve, metadata, deploy-to-assistant, cancel with confirmation, retry for failures and a log console, plus a new-job dialog with a cost estimate.
Eve agent that turns a PDF into study flash cards, with optional AI-generated images per concept.
Flue agent that turns a PDF into study flash cards through a workflow, with optional AI-generated images per concept.
LangGraph agent that turns a PDF into study flash cards, with optional AI-generated images per concept.
Mastra agent that turns a PDF into study flash cards, with optional AI-generated images per concept.
Compact floating chat bubble that expands into a mini chat window. Features smooth expand/collapse animation, pulsing notification dot, and a complete mini chat interface inside. Ideal for customer support overlays.
A full recreation of the Gemini chat built from the Gemini components on shadcn Base UI.
Browse 160,000+ HuggingFace GGUF models and the curated wllama catalog, inspect any file's metadata via a ~4KB HTTP Range read (checkGGUFBrowserCompatFromURL — never a model download), get a browser-compat verdict, and hand a model off to the chat block. Consumes the PROMOTED @localmode/wllama model-discovery utils (searchGGUFModels / listGGUFFiles / HFApiError) instead of a block-local hf-api.ts; keeps a justified block-local chat-handoff emitter (handoff.ts). Cursor pagination, typed search errors + retry, and an explicit Download-to-cache prefetch. No model bytes on load. Split from ui/blocks/device-model-lab (GGUF explorer section).
Showing 289–312 of 468