← Back to Skills Marketplace
Agent Ui
by
Ömer Karışman
· GitHub ↗
· v0.1.5
1992
Downloads
2
Stars
11
Active Installs
4
Versions
Install in OpenClaw
/install agent-ui
Description
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Cap...
README (SKILL.md)
Agent Component
Batteries-included agent component from ui.inference.sh.

Quick Start
# Install the agent component
npx shadcn@latest add https://ui.inference.sh/r/agent.json
# Add the SDK for the proxy route
npm install @inferencesh/sdk
Setup
1. API Proxy Route (Next.js)
// app/api/inference/proxy/route.ts
import { route } from '@inferencesh/sdk/proxy/nextjs';
export const { GET, POST, PUT } = route;
2. Environment Variable
# .env.local
INFERENCE_API_KEY=inf_...
3. Use the Component
import { Agent } from "@/registry/blocks/agent/agent"
export default function Page() {
return (
\x3CAgent
proxyUrl="/api/inference/proxy"
agentConfig={{
core_app: { ref: 'openrouter/claude-haiku-45@0fkg6xwb' },
description: 'a helpful ai assistant',
system_prompt: 'you are helpful.',
}}
/>
)
}
Features
| Feature | Description |
|---|---|
| Runtime included | No backend logic needed |
| Tool lifecycle | Pending, progress, approval, results |
| Human-in-the-loop | Built-in approval flows |
| Widgets | Declarative JSON UI from agent responses |
| Streaming | Real-time token streaming |
| Client-side tools | Tools that run in the browser |
Client-Side Tools Example
import { Agent } from "@/registry/blocks/agent/agent"
import { createScopedTools } from "./blocks/agent/lib/client-tools"
const formRef = useRef\x3CHTMLFormElement>(null)
const scopedTools = createScopedTools(formRef)
\x3CAgent
proxyUrl="/api/inference/proxy"
config={{
core_app: { ref: 'openrouter/claude-haiku-45@0fkg6xwb' },
tools: scopedTools,
system_prompt: 'You can fill forms using scan_ui and fill_field tools.',
}}
/>
Props
| Prop | Type | Description |
|---|---|---|
proxyUrl |
string | API proxy endpoint |
name |
string | Agent name (optional) |
config |
AgentConfig | Agent configuration |
allowFiles |
boolean | Enable file uploads |
allowImages |
boolean | Enable image uploads |
Related Skills
# Chat UI building blocks
npx skills add inference-sh/skills@chat-ui
# Declarative widgets from JSON
npx skills add inference-sh/skills@widgets-ui
# Tool lifecycle UI
npx skills add inference-sh/skills@tools-ui
Documentation
- Agents Overview - Building AI agents
- Agent SDK - Programmatic agent control
- Human-in-the-Loop - Approval flows
- Agents That Generate UI - Building generative UIs
- Agent UX Patterns - Best practices
Component docs: ui.inference.sh/blocks/agent
Usage Guidance
This appears to be a legitimate UI component for building agent interfaces, but check a few things before installing: (1) Verify the source URLs and npm package (@inferencesh/sdk) on the public registries (npm, the inference.sh domain) to ensure they are the expected projects. (2) Inspect the agent.json that npx will fetch (and any code it adds) before running it in your app. (3) The SKILL.md requires INFERENCE_API_KEY but the registry metadata doesn't declare it — confirm which API key is needed (inference.sh vs OpenRouter) and limit its scope. (4) Store API keys safely (use env or secrets manager) and rotate them if you later suspect misuse. (5) If you have security concerns, run the add/install steps in an isolated environment or review the fetched files in a code review before merging into a production codebase.
Capability Analysis
Type: OpenClaw Skill
Name: agent-ui
Version: 0.1.5
The skill bundle is suspicious due to its reliance on external resources and commands that fetch and execute code from third-party domains. Specifically, `SKILL.md` instructs the user to run `npx shadcn@latest add https://ui.inference.sh/r/agent.json`, which fetches and potentially executes code from `ui.inference.sh`. While this is a common pattern for component installation, it introduces a significant supply chain risk. Additionally, the skill integrates an API proxy route and requires an API key for `inference.sh` services, and allows for file uploads, which could introduce vulnerabilities if not handled securely by the integrating application. There is no direct evidence of intentional malicious behavior within the provided files, but the broad external dependencies and execution capabilities warrant a 'suspicious' classification.
Capability Assessment
Purpose & Capability
Name/description match the instructions: this is a UI component for React/Next.js that uses an API proxy and an SDK. Declared runtime steps (npx shadcn template, install @inferencesh/sdk, add a Next.js proxy route) are coherent with building an agent UI.
Instruction Scope
SKILL.md instructs running npx to fetch a remote agent.json and npm install of @inferencesh/sdk and shows adding an .env.local INFERENCE_API_KEY and a Next.js proxy route. The instructions do not request unrelated system files or broad data exfiltration, but they do instruct pulling third-party code at install time and storing an API key in .env.local.
Install Mechanism
This is an instruction-only skill (no install spec). The install steps use npx shadcn@latest add https://ui.inference.sh/r/agent.json and npm install @inferencesh/sdk — pulling code from inference.sh and npm is expected for this purpose, but those are network operations that will fetch code into your project (review the fetched JSON/package before running).
Credentials
Registry metadata lists no required env vars, but SKILL.md explicitly instructs adding INFERENCE_API_KEY in .env.local. This mismatch reduces transparency. Also the example agent_config references an external model (openrouter/claude-haiku-45), which could require a different service key; the SKILL.md does not clearly state which credential(s) are required or their scope.
Persistence & Privilege
Skill does not request always:true, does not declare special config paths, and is user-invocable. It does not ask to modify other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent-ui - After installation, invoke the skill by name or use
/agent-ui - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.5
- Added SKILL.md with an overview, setup instructions, and feature list for the agent-ui React/Next.js component.
- Documents installation, environment setup, and usage with code examples.
- Lists key features: drop-in agent, tool lifecycle, human-in-the-loop, real-time streaming, and client-side tools.
- Provides details on props, related skills, and links to further documentation.
v0.1.1
- Updated SKILL.md to reference correct related skills package names: changed commands from inference-sh/skills@* to inference-sh/agent-skills@*.
- No changes to functionality or code—documentation update only.
v0.1.0
- Initial release of agent-ui skill.
- Provides a batteries-included agent component for React/Next.js with runtime, tools, streaming, approvals, and widgets built in.
- Enables building AI chat interfaces, agentic UIs, SaaS copilots, and assistants with a single drop-in component.
- Supports human-in-the-loop approval flows and client-side tools for form filling and declarative UI.
- Includes comprehensive documentation and setup instructions for rapid integration.
v1.0.0
agent-ui 1.0.0
- Initial release of a batteries-included agent component for React/Next.js from ui.inference.sh.
- Provides a drop-in agent with runtime, streaming, human-in-the-loop approvals, tools, and widgets built in.
- Supports quick integration with API proxy setup and environment variables.
- Enables client-side tools for form filling and browser-side automation.
- Designed for building AI chat interfaces, assistants, copilot UIs, and agentic applications.
Metadata
Frequently Asked Questions
What is Agent Ui?
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Cap... It is an AI Agent Skill for Claude Code / OpenClaw, with 1992 downloads so far.
How do I install Agent Ui?
Run "/install agent-ui" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agent Ui free?
Yes, Agent Ui is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Agent Ui support?
Agent Ui is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agent Ui?
It is built and maintained by Ömer Karışman (@okaris); the current version is v0.1.5.
More Skills