DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to add agent status and chat components to an AI app with Solid Glass

Install Solid Glass's agent-focused components for status, steps, diffs and questions.

Who it is forA developer building an AI agent or chat interface who needs to show streaming responses, tool steps and human questions.

The problemAI interfaces need to show an agent's status, steps, diffs and pending questions, and generic components do not cover these.

The outcomeThe app has ready-made components for turn status, a composer, tool steps, diffs, ask cards, context usage, task notices and reasoning.

What you need first

  • Node.js and npm
  • A shadcn/ui project with React 19, Tailwind CSS 4 and the Base UI components
  • Git, if you want to run the site from a local clone

Steps

  1. Install the status glyph by running npx shadcn@latest add deeplethe/solid-glass/status-glyph.
  2. Add the other components you need, for example npx shadcn@latest add deeplethe/solid-glass/tool-steps. (inferred, check the README)
  3. Use turn-status for the agent's status line and composer for the input box.
  4. Use ask-card for questions the agent asks, and context-ring for how full its context is.
  5. Check each component renders in the app's light and dark modes.

Prompt for your agent

In the React project at <project-path>, install the Solid Glass components `turn-status`, `composer`, `tool-steps` and `ask-card` from the deeplethe/solid-glass registry with `npx shadcn@latest add deeplethe/solid-glass/<component>`. Report which files were created and confirm the project still builds.

Caveat. The components are built for interfaces where an agent works, so they assume a React 19 and Tailwind CSS 4 setup as the README describes.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page