autogpt-agents

Build and deploy continuous autonomous agents using the AutoGPT visual workflow platform.

1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/Clay-HHK/claude-skills --skill autogpt-agents-clay-hhk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: autogpt-agents
Source: https://github.com/Clay-HHK/claude-skills/tree/main/autogpt
Command: npx skills add https://github.com/Clay-HHK/claude-skills --skill autogpt-agents-clay-hhk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires autogpt-platform, and includes references (resource) components.

What problem does it solve? Building autonomous AI agents that run continuously and respond to external triggers requires significant infrastructure work, from orchestration to credential management. This Skill guides you through the AutoGPT platform so you can create, deploy, and monitor persistent agents without building that plumbing yourself. ## Core Features & Use Cases - Visual Agent Builder: Compose agents as graphs of connected blocks (LLM calls, webhooks, integrations) through a drag-and-drop interface or programmatically via the REST API. - Continuous Execution & Triggers: Run agents persistently with manual API calls, webhook triggers, or cron-style schedules, monitored via WebSocket updates. - Forge Toolkit & Benchmarking: Develop custom agents and abilities with the Forge toolkit, then validate performance with the agbenchmark framework. - Use Case: You want an agent that monitors a GitHub repository via webhook, summarizes new issues with an LLM, and posts results to Discord on a schedule. This Skill walks you through wiring those blocks, adding credentials, and deploying with Docker Compose. ## Quick Start Use the autogpt skill to help me build an agent that summarizes new GitHub issues and posts them to Discord.

Frequently Asked Questions about autogpt-agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an autonomous agent with AutoGPT?▼

Start the AutoGPT Platform with Docker Compose, open the visual builder at localhost:3000, add blocks from the BlocksControl panel, connect nodes by dragging between handles, configure inputs, and run the agent. Agents are graphs of nodes containing reusable blocks.

AutoGPT vs LangChain vs CrewAI for building agents?▼

AutoGPT suits continuous agents with visual workflows, triggers, and a marketplace of pre-built blocks. LangChain or LlamaIndex give more control over agent logic in code, while CrewAI targets role-based multi-agent collaboration.

Can AutoGPT agents run on a schedule or respond to webhooks?▼

Yes. Agents support three trigger types: manual execution via POST to the graph execute endpoint, webhook triggers via POST to a webhook URL, and cron-style scheduled execution defined with a schedule expression and graph ID.

Why is my AutoGPT agent execution stuck in queued status?▼

Stuck executions usually mean the executor service is down or the RabbitMQ queue is backlogged. Check executor logs with docker compose logs executor, inspect queues at the RabbitMQ management UI on port 15672, and restart or scale the executor service.

How do I add API credentials like OpenAI keys to AutoGPT blocks?▼

Navigate to Profile > Integrations in the frontend, select the provider such as OpenAI, GitHub, or Google, and enter API keys or authorize OAuth. Credentials are encrypted and automatically injected into blocks that declare the required provider.