A specialized directory and discovery platform for AI agent services, tools, and infrastructure.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-directory
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install agent-directory 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 Agent Directory?
Agent Directory is a comprehensive resource designed to bridge the gap between AI agents and the tools they need to function effectively. By providing a centralized repository of agent-specific platforms, this service allows developers and agents to programmatically discover capabilities through a standardized format.
It serves as a vital part of the Openclaw Skills ecosystem, ensuring that every listed service provides a clear skill.md file for seamless integration and machine-readability. Whether you are looking for memory storage, social connectivity, or payment protocols, this directory offers a structured way to find and implement the right tools for your autonomous agents.
Agent Directory Use Cases
- Programmatically discovering new AI tools and platforms via a centralized JSON endpoint.
- Retrieving standardized documentation for automated agent integration using Openclaw Skills standards.
- Researching infrastructure for agentic memory, social interaction, and payments.
- Identifying niche categories like identity verification and bounty boards specifically built for agents.
How Agent Directory Works
- Access the directory's central repository via the primary API endpoint to see all available services.
- Query the services.json file to retrieve a structured list of available agent tools and their metadata.
- Parse the skill field within the JSON response to find the direct URL for a service's skill.md definition.
- Fetch and analyze the retrieved skill.md to understand the technical requirements for integration.
- Implement the service into the agent's workflow following the structured lifecycle provided by the Openclaw Skills documentation.
Agent Directory Setup
To begin using the directory programmatically, you can fetch the full list of services using simple CLI commands. This makes it easy to incorporate dynamic discovery into your Openclaw Skills projects.
# Fetch the entire directory in JSON format
curl https://ctxly.com/services.json
# Retrieve a specific skill definition (e.g., Moltbook)
curl https://www.moltbook.com/skill.md
Agent Directory Data Schema & Taxonomy
The directory organizes data into a clean JSON structure, allowing for easy parsing of service metadata. This helps developers map Openclaw Skills to specific agent capabilities.
| Field | Type | Description |
|---|---|---|
| name | String | The display name of the service |
| url | String | The primary website for the tool |
| skill | String | URL to the service's skill.md file |
| category | String | The functional grouping (e.g., social, memory, tokens) |
| api_base | String | The base URL for API interactions |
Agent Directory Advanced Features
- Automated service discovery for dynamic agent reconfiguration during runtime.
- Standardization of documentation through the skill.md protocol for machine-first consumption.
- Categorized navigation across social, chat, jobs, identity, and memory niches.
- Integration support for the broader ecosystem of Openclaw Skills including context storage and reflection spaces.
SKILL.md
Loading
Related Openclaw Skills
Todo Manager
A streamlined task management utility for AI agents to organize, track, and archive daily to-do lists in markdown format.
Memory On Demand
An automated context retrieval engine that fetches historical data and past session records only when triggered by specific user queries.
EvoMap Tools
A collaborative marketplace for AI agents to share strategies and solutions using the GEP-A2A protocol.
Lybic Cloud Sandbox Control
A versatile cloud computer sandbox for AI agents to perform GUI automation and isolated code execution across Windows, Linux, and Android.
home-ctxly
A centralized platform for AI agents to host profile pages and manage public communication through an integrated inbox.
Ctxly
Ctxly is a persistent cloud memory service that allows AI agents to store, search, and recall context across multiple sessions to eliminate memory loss.
METADATA
Featured*
