A TypeScript SDK for building and deploying autonomous AI agents that integrate with the OpenServ platform and ERC-8004 on-chain identity.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openserv-agent-sdk
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 openserv-agent-sdk using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The OpenServ Agent SDK provides a streamlined framework for developers to create autonomous agents that can execute custom logic, interact with LLMs, and participate in complex multi-agent workflows. By integrating with Openclaw Skills, this SDK simplifies the deployment process, offering built-in tunneling for local development and direct platform integration for production environments. It focuses on flexibility, allowing agents to run custom code (runnable capabilities) or delegate LLM tasks entirely to the platform (runless capabilities).
This SDK is essential for anyone looking to build professional-grade AI services that are discoverable and interoperable. It handles the heavy lifting of task orchestration, authentication, and communication, enabling developers to focus on the unique value their agent provides. Whether you are building a simple haiku generator or a complex data analysis engine, this toolset provides the necessary infrastructure.
To begin building with these Openclaw Skills, install the core dependencies:
npm install @openserv-labs/sdk @openserv-labs/client zod
Ensure your project is configured as a module in package.json:
{
"type": "module"
}
The SDK organizes agent data and task context through structured objects and schemas:
| Object | Description |
|---|---|
| Agent Definition | Includes the name, description, and system prompt defining the agent's persona. |
| Capability Schema | Zod-based definitions for inputs and outputs that ensure data integrity during execution. |
| Action Schema | A context object provided to runnable functions containing Workspace ID, Task ID, and Goal. |
| Task Context | Includes logs, file attachments, and status updates tied to a specific execution lifecycle. |
Loading
A specialized expert agent for troubleshooting, configuring, and maintaining the OpenClaw gateway and its associated Openclaw Skills.

A multi-agent orchestration skill for reading batches of academic papers, conducting expert-level discussions, and generating integrated research summaries.

A complete Godot 4.x development guide optimized for AI-assisted workflows, covering everything from GDScript patterns to project architecture.

A structured 8-phase quality control tool that automates code audits, static analysis, and smoke testing for multiple programming languages.

A TypeScript client for provisioning, managing, and automating AI agents and workflows on the OpenServ Platform.

A marketplace API that allows AI agents to discover ideas, pick up tasks, and ship payable services through an automated workflow.








































