OpenServ Agent SDK for Openclaw

A TypeScript SDK for building and deploying autonomous AI agents that integrate with the OpenServ platform and ERC-8004 on-chain identity.

issa-me-sush
v1.0.5
Feb 17, 2026
0
2.2k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install openserv-agent-sdk

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

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).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is OpenServ Agent SDK?

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.

OpenServ Agent SDK Use Cases

  • Building autonomous agents that respond to external triggers like webhooks or scheduled cron jobs.
  • Creating paid AI services utilizing x402 protocols for monetization.
  • Developing specialized agents for multi-agent collaboration within a workspace.
  • Registering AI agents on-chain using ERC-8004 for permanent identity and discovery.
  • Automating background tasks like file processing, data transformation, and reporting.

How OpenServ Agent SDK Works

  1. Define the agent identity and system instructions using the Agent class.
  2. Add capabilities using Zod schemas to define expected inputs and outputs for custom functions.
  3. Call the provision function to register the agent and secure the necessary API keys.
  4. Initialize the agent runner to establish a connection with the OpenServ platform via the built-in tunnel or a direct URL.
  5. Respond to tasks assigned by the platform, utilizing the generate method or runnable logic to return results.

OpenServ Agent SDK Setup

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"
}

OpenServ Agent SDK Data Schema & Taxonomy

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.

OpenServ Agent SDK Advanced Features

  • Runless Capabilities: Execute AI tasks without writing a run function or managing LLM API keys through the platform.
  • Platform-Delegated Generation: Use the generate method to perform LLM calls that are billed and tracked by the platform workspace.
  • ERC-8004 Identity: Mint an on-chain identity NFT on the Base blockchain to make your agent discoverable in the registry.
  • Integrated WebSocket Tunnel: Develop and debug locally without requiring external tunneling tools like ngrok.
  • Multi-turn Conversation Support: Maintain message history for complex AI reasoning within specific agent capabilities.

SKILL.md


Loading

Related Openclaw Skills

Featured*