A commerce layer for AI agents to discover and pay for APIs via natural language and micro-billing.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agentclear
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install agentclear using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
AgentClear acts as the unified commerce layer for AI agents, simplifying how tools and services are consumed. It provides a bridge between autonomous agents and paid API services, allowing agents to find the right tool for a task using natural language and pay for usage on a per-call basis. By integrating this with your Openclaw Skills library, you remove the friction of managing dozens of individual API subscriptions.
The platform features a proxy system that handles authentication and billing automatically, ensuring developers only pay for what their agents actually use. Whether you need specialized document parsing or complex data analysis, AgentClear provides a secure, HTTPS-encrypted pipeline for service discovery and execution.
Obtain an API key (starting with axk_) from the official website and set it as an environment variable to use with your Openclaw Skills.
export AGENTCLEAR_API_KEY="axk_your_key_here"
New accounts typically receive $5 in free credits to begin testing API discovery and proxy calls immediately.
AgentClear organizes data into three primary buckets to facilitate commerce for Openclaw Skills:
| Data Type | Description |
|---|---|
| Discovery Metadata | Includes service ID, name, description, price per call, and trust scores. |
| Billing Metadata | Service ID, timestamp, and cost; request/response payloads are not stored. |
| Account Data | API key scoping and account balance tracking for micro-transactions. |
Loading
A streamlined, SQLite-powered task manager designed for efficient CLI-based workflow organization and status tracking.

An automated assistant for Wolt.com that handles restaurant discovery, complex group ordering, and real-time delivery tracking.

A slow-channel communication bridge that allows AI agents to leave non-urgent messages and decision requests for their human operators.

A dedicated slow-channel notification system that queues non-urgent agent updates for structured human review.

A powerful metasearch CLI skill for AI agents to retrieve clean web, news, image, and video data using the duckse engine.

A professional content management skill for React-based digital gardens that automates MDX authoring and Obsidian-like documentation workflows.








































