🤖

Agents

Autonomous AI workflows and assistants that combine multiple skills to accomplish complex tasks.

3,426 total · 291 safe · 165 malicious

🤖

Shellbot Video Generator

by cohnen

5

This skill helps you create professional motion graphics videos using React and Remotion, by scraping website data for branding and then generating video content.

suspicious AI & LLMs
0
🤖

Agent Safety

by compass-soul

4

This skill helps prevent accidental leaks of sensitive information like API keys and personal data when committing code or performing system checks.

suspicious AI & LLMs
0
🤖

Agent Architect

by contrario

5

This skill helps your AI agent break down complex goals into smaller steps, execute them, and self-correct if issues arise, aiming to make agents more autonomous.

suspicious AI & LLMs
0
🤖

Siphonclaw

by curtisgc1

5

SiphonClaw helps you organize and search your documents using AI, allowing you to ingest PDFs, images, and spreadsheets into a searchable knowledge base and find information using text and visual search.

suspicious Search & Research
0
🤖

Video News Downloader

by cyberpsychosissss

5

This skill automatically downloads daily news videos from YouTube, processes their subtitles using AI, and makes them available for local streaming.

suspicious AI & LLMs
0
🤖

Self Improving Agent 1 0 5

by czubi1928

5

This agent helps improve itself by logging errors, user corrections, and feature requests into markdown files for later review and integration.

suspicious Uncategorized
0
🤖

Nadmail

by daaab

4

This skill allows AI agents to send and receive emails within the Monad ecosystem, with features for autonomous registration and micro-investments in meme coins.

suspicious Communication
0
🤖

Walletconnect Agent

by daaab

4

Connects your AI agent to Web3 applications to automatically perform actions like swapping tokens or minting NFTs using WalletConnect.

suspicious AI & LLMs
0
🤖

X402 Agent Marketplace

by dahhan43-netizen

4

This skill acts as a marketplace for AI agents that provide cryptocurrency market analysis and trading signals, using SOL cryptocurrency for payments.

suspicious AI & LLMs
0
🤖

Openclaw Growth Pack

by dalomeve

4

This skill helps stabilize and improve the performance of the OpenClaw agent by adjusting its configuration and execution settings.

suspicious Productivity & Tasks
0
🤖

Rust Rebuilder

by dandandujie

5

Helps users rewrite existing projects into Rust by planning and executing incremental rewrites with architecture mapping and verification.

suspicious Smart Home & IoT
0
🤖

Openclaw Kirocli Coding Agent

by dandysuper

4

This skill allows you to run various AI coding assistants like Codex, Claude, and Kiro CLI from your terminal to help with programming tasks.

suspicious AI & LLMs
0
🤖

Obsidian Official Cli Headless

by darinrowe

4

Installs and configures the official Obsidian CLI for use on headless Linux servers without a graphical interface.

suspicious Notes & PKM
0
🤖

Clawsec Suite

by davida-ps

4

This skill acts as a security manager for other skills, monitoring for advisories about malicious software and requiring user approval before taking action.

suspicious AI & LLMs
0
🤖

Aegis Shield

by deegerwalker

4

This tool scans text for potentially harmful content before it's used or saved, and provides a secure way to add information to your memory.

suspicious Image & Video Generation
0
🤖

Hyperbot Quote Mcp

by develophyperbotnetwork

4

This skill provides cryptocurrency trading data analytics, including smart money tracking, whale monitoring, and market data queries, by connecting to the Hyperbot platform.

suspicious Finance
0
🤖

Memory Scan

by dgriffin831

4

This tool scans your agent's memory files for potential security threats like leaked credentials or malicious instructions.

suspicious AI & LLMs
0
🤖

Wodeapp Ai

by diankourenxia

5

This skill acts as a unified engine to access and manage over 343 AI models for text, image, video, and more, with features for building websites and workflows.

suspicious AI & LLMs
0
🤖

Multi Workplace

by dickwu

5

Manages multiple project directories (workplaces) with isolated agent environments, allowing you to switch between projects and manage agents within each.

suspicious Communication
0
🤖

Workplace

by dickwu

4

Manages multiple project directories (workplaces) with isolated agents, memory, and communication features, integrating with chat platforms and IDEs.

suspicious Communication
0
🤖

Apix

by dngpng

4

This tool helps you discover, inspect, and execute API endpoints from local markdown files directly from your terminal.

suspicious CLI Utilities
0
🤖

Openclaw Anything

by doanbactam

5

This skill acts as a command-line interface helper for the OpenClaw platform, providing documentation and wrapping common commands.

suspicious Search & Research
0
🤖

Feishu Doc Collab

by dongweiii

4

This skill enables real-time AI collaboration within Feishu (Lark) documents by automatically responding to edits and messages using a structured in-document protocol.

suspicious AI & LLMs
0
🤖

Ralph Ultra

by dorukardahan

4

Performs a comprehensive, multi-hour security audit of your code and infrastructure, covering various attack vectors and compliance aspects.

suspicious AI & LLMs
0

What Are OpenClaw Agents?

OpenClaw agents are autonomous AI workflows that combine multiple skills to accomplish complex tasks. Unlike individual skills which provide a single capability, agents orchestrate multiple skills together — planning steps, maintaining context through OpenClaw's Memory component, and executing multi-step workflows without human intervention.

Agents range from simple task automators to sophisticated assistants that can handle research, code generation, data analysis, and more. ClawGrid security-scores every agent so you can install with confidence.

Agents FAQ

What are OpenClaw agents?

Agents are autonomous AI workflows that combine multiple skills to accomplish complex tasks. They can plan, reason, and execute multi-step workflows without human intervention. Read our guide to skills, agents, and assistants.

How are agents different from skills?

Skills are individual capabilities (e.g., "read a file" or "query a database"). Agents combine multiple skills into autonomous workflows — they can plan, reason, and execute multi-step tasks. Think of skills as tools and agents as the workers who use them.

Can I build my own OpenClaw agent?

Yes — agents are defined using YAML configuration that specifies which skills to use, which LLM to run, and how to handle tasks. You can publish agents to ClawHub for others to discover. See our getting started guide.