npx skills add ...
npx skills add davila7/claude-code-templates --skill autogpt-agents
npx skills add davila7/claude-code-templates --skill autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
The same skill content is published under more than one repo. The install counts are split across them; any of these commands works.
Comprehensive platform for building, deploying, and managing continuous AI agents through a visual interface or development toolkit.
Use AutoGPT when:
Key features:
Use alternatives instead:
AutoGPT has two main systems:
Agents are represented as graphs containing nodes connected by links:
Blocks are reusable functional components:
| Block Type | Purpose |
|---|---|
INPUT | Agent entry points |
OUTPUT | Agent outputs |
AI | LLM calls, text generation |
WEBHOOK | External triggers |
STANDARD | General operations |
AGENT | Nested agent execution |
AI Blocks:
AITextGeneratorBlock - Generate text with LLMsAIConversationBlock - Multi-turn conversationsSmartDecisionMakerBlock - Conditional logicIntegration Blocks:
Control Blocks:
Manual execution:
Webhook trigger:
Scheduled execution:
WebSocket updates:
REST API polling:
Benchmarks use recorded HTTP responses for reproducibility:
Blocks automatically access user credentials:
| Provider | Auth Type | Use Cases |
|---|---|---|
| OpenAI | API Key | LLM, embeddings |
| Anthropic | API Key | Claude models |
| GitHub | OAuth | Code, repos |
| OAuth | Drive, Gmail, Calendar | |
| Discord | Bot Token | Messaging |
| Notion | OAuth | Documents |
| Variable | Purpose |
|---|---|
DATABASE_URL | PostgreSQL connection |
REDIS_URL | Redis connection |
RABBITMQ_URL | RabbitMQ connection |
ENCRYPTION_KEY | Credential encryption |
SUPABASE_URL | Authentication |
Services not starting:
Database connection issues:
Agent execution stuck:
Graph (Agent)
├── Node (Input)
│ └── Block (AgentInputBlock)
├── Node (Process)
│ └── Block (LLMBlock)
├── Node (Decision)
│ └── Block (SmartDecisionMaker)
└── Node (Output)
└── Block (AgentOutputBlock)User/Trigger → Graph Execution → Node Execution → Block.execute()
↓ ↓ ↓
Inputs Queue System Output YieldsPOST /api/v1/graphs/{graph_id}/execute
Content-Type: application/json
{
"inputs": {
"input_name": "value"
}
}POST /api/v1/webhooks/{webhook_id}
Content-Type: application/json
{
"data": "webhook payload"
}{
"schedule": "0 */2 * * *",
"graph_id": "graph-uuid",
"inputs": {}
}const ws = new WebSocket('ws://localhost:8001/ws');
ws.onmessage = (event) => {
const update = JSON.parse(event.data);
console.log(`Node ${update.node_id}: ${update.status}`);
};GET /api/v1/executions/{execution_id}# Setup forge environment
cd classic
./run setup
# Create new agent from template
./run forge create my-agent
# Start agent server
./run forge start my-agentmy-agent/
├── agent.py # Main agent logic
├── abilities/ # Custom abilities
│ ├── __init__.py
│ └── custom.py
├── prompts/ # Prompt templates
└── config.yaml # Agent configurationfrom forge import Ability, ability
@ability(
name="custom_search",
description="Search for information",
parameters={
"query": {"type": "string", "description": "Search query"}
}
)
def custom_search(query: str) -> str:
"""Custom search ability."""
# Implement search logic
result = perform_search(query)
return result# Run all benchmarks
./run benchmark
# Run specific category
./run benchmark --category coding
# Run with specific agent
./run benchmark --agent my-agent# Record new cassettes
./run benchmark --record
# Run with existing cassettes
./run benchmark --playbackclass MyLLMBlock(Block):
def execute(self, inputs):
# Credentials are injected by the system
credentials = self.get_credentials("openai")
client = OpenAI(api_key=credentials.api_key)
# ...# docker-compose.prod.yml
services:
rest_server:
image: autogpt/platform-backend
environment:
- DATABASE_URL=postgresql://...
- REDIS_URL=redis://redis:6379
ports:
- "8006:8006"
executor:
image: autogpt/platform-backend
command: poetry run executor
frontend:
image: autogpt/platform-frontend
ports:
- "3000:3000"cd autogpt_platform/backend
poetry run cli gen-encrypt-key# Check container status
docker compose ps
# View logs
docker compose logs rest_server
# Restart services
docker compose restart# Run migrations
cd backend
poetry run prisma migrate deploy# Check RabbitMQ queue
# Visit http://localhost:15672 (guest/guest)
# Clear stuck executions
docker compose restart executor