AutoGPT - Autonomous AI Agent Platform

Comprehensive platform for building, deploying, and managing continuous AI agents through a visual interface or development toolkit.

When to use AutoGPT

Use AutoGPT when:

• Building autonomous agents that run continuously
• Creating visual workflow-based AI agents
• Deploying agents with external triggers (webhooks, schedules)
• Building complex multi-step automation pipelines
• Need a no-code/low-code agent builder

Key features:

• Visual Agent Builder: Drag-and-drop node-based workflow editor
• Continuous Execution: Agents run persistently with triggers
• Marketplace: Pre-built agents and blocks to share/reuse
• Block System: Modular components for LLM, tools, integrations
• Forge Toolkit: Developer tools for custom agent creation
• Benchmark System: Standardized agent performance testing

Use alternatives instead:

• LangChain/LlamaIndex: If you need more control over agent logic
• CrewAI: For role-based multi-agent collaboration
• OpenAI Assistants: For simple hosted agent deployments
• Semantic Kernel: For Microsoft ecosystem integration

Quick start

Installation (Docker)

 1# Clone repository
 2git clone https://github.com/Significant-Gravitas/AutoGPT.git
 3cd AutoGPT/autogpt_platform
 4
 5# Copy environment file
 6cp .env.example .env
 7
 8# Start backend services
 9docker compose up -d --build
10
11# Start frontend (in separate terminal)
12cd frontend
13cp .env.example .env
14npm install
15npm run dev

Access the platform

• Frontend UI: http://localhost:3000
• Backend API: http://localhost:8006/api
• WebSocket: ws://localhost:8001/ws

Architecture overview

AutoGPT has two main systems:

AutoGPT Platform (Production)

• Visual agent builder with React frontend
• FastAPI backend with execution engine
• PostgreSQL + Redis + RabbitMQ infrastructure

AutoGPT Classic (Development)

• Forge: Agent development toolkit
• Benchmark: Performance testing framework
• CLI: Command-line interface for development

Core concepts

Graphs and nodes

Agents are represented as graphs containing nodes connected by links:

Graph (Agent)
  ├── Node (Input)
  │   └── Block (AgentInputBlock)
  ├── Node (Process)
  │   └── Block (LLMBlock)
  ├── Node (Decision)
  │   └── Block (SmartDecisionMaker)
  └── Node (Output)
      └── Block (AgentOutputBlock)

Blocks

Blocks are reusable functional components:

Execution flow

User/Trigger → Graph Execution → Node Execution → Block.execute()
     ↓              ↓                 ↓
  Inputs      Queue System      Output Yields

Building agents

Using the visual builder

1. Open Agent Builder at http://localhost:3000
2. Add blocks from the BlocksControl panel
3. Connect nodes by dragging between handles
4. Configure inputs in each node
5. Run agent using PrimaryActionBar

Available blocks

AI Blocks:

• AITextGeneratorBlock - Generate text with LLMs
• AIConversationBlock - Multi-turn conversations
• SmartDecisionMakerBlock - Conditional logic

Integration Blocks:

• GitHub, Google, Discord, Notion connectors
• Webhook triggers and handlers
• HTTP request blocks

Control Blocks:

• Input/Output blocks
• Branching and decision nodes
• Loop and iteration blocks

Agent execution

Trigger types

Manual execution:

1POST /api/v1/graphs/{graph_id}/execute
2Content-Type: application/json
3
4{
5  "inputs": {
6    "input_name": "value"
7  }
8}

Webhook trigger:

1POST /api/v1/webhooks/{webhook_id}
2Content-Type: application/json
3
4{
5  "data": "webhook payload"
6}

Scheduled execution:

1{
2  "schedule": "0 */2 * * *",
3  "graph_id": "graph-uuid",
4  "inputs": {}
5}

Monitoring execution

WebSocket updates:

1const ws = new WebSocket('ws://localhost:8001/ws');
2
3ws.onmessage = (event) => {
4  const update = JSON.parse(event.data);
5  console.log(`Node ${update.node_id}: ${update.status}`);
6};

REST API polling:

1GET /api/v1/executions/{execution_id}

Using Forge (Development)

Create custom agent

1# Setup forge environment
2cd classic
3./run setup
4
5# Create new agent from template
6./run forge create my-agent
7
8# Start agent server
9./run forge start my-agent

Agent structure

my-agent/
├── agent.py          # Main agent logic
├── abilities/        # Custom abilities
│   ├── __init__.py
│   └── custom.py
├── prompts/          # Prompt templates
└── config.yaml       # Agent configuration

Implement custom ability

 1from forge import Ability, ability
 2
 3@ability(
 4    name="custom_search",
 5    description="Search for information",
 6    parameters={
 7        "query": {"type": "string", "description": "Search query"}
 8    }
 9)
10def custom_search(query: str) -> str:
11    """Custom search ability."""
12    # Implement search logic
13    result = perform_search(query)
14    return result

Benchmarking agents

Run benchmarks

1# Run all benchmarks
2./run benchmark
3
4# Run specific category
5./run benchmark --category coding
6
7# Run with specific agent
8./run benchmark --agent my-agent

Benchmark categories

• Coding: Code generation and debugging
• Retrieval: Information finding
• Web: Web browsing and interaction
• Writing: Text generation tasks

VCR cassettes

Benchmarks use recorded HTTP responses for reproducibility:

1# Record new cassettes
2./run benchmark --record
3
4# Run with existing cassettes
5./run benchmark --playback

Integrations

Adding credentials

1. Navigate to Profile > Integrations
2. Select provider (OpenAI, GitHub, Google, etc.)
3. Enter API keys or authorize OAuth
4. Credentials are encrypted and stored securely

Using credentials in blocks

Blocks automatically access user credentials:

1class MyLLMBlock(Block):
2    def execute(self, inputs):
3        # Credentials are injected by the system
4        credentials = self.get_credentials("openai")
5        client = OpenAI(api_key=credentials.api_key)
6        # ...

Supported providers

Deployment

Docker production setup

 1# docker-compose.prod.yml
 2services:
 3  rest_server:
 4    image: autogpt/platform-backend
 5    environment:
 6      - DATABASE_URL=postgresql://...
 7      - REDIS_URL=redis://redis:6379
 8    ports:
 9      - "8006:8006"
10
11  executor:
12    image: autogpt/platform-backend
13    command: poetry run executor
14
15  frontend:
16    image: autogpt/platform-frontend
17    ports:
18      - "3000:3000"

Environment variables

Generate encryption key

1cd autogpt_platform/backend
2poetry run cli gen-encrypt-key

Best practices

1. Start simple: Begin with 3-5 node agents
2. Test incrementally: Run and test after each change
3. Use webhooks: External triggers for event-driven agents
4. Monitor costs: Track LLM API usage via credits system
5. Version agents: Save working versions before changes
6. Benchmark: Use agbenchmark to validate agent quality

Common issues

Services not starting:

1# Check container status
2docker compose ps
3
4# View logs
5docker compose logs rest_server
6
7# Restart services
8docker compose restart

Database connection issues:

1# Run migrations
2cd backend
3poetry run prisma migrate deploy

Agent execution stuck:

1# Check RabbitMQ queue
2# Visit http://localhost:15672 (guest/guest)
3
4# Clear stuck executions
5docker compose restart executor

References

• Advanced Usage - Custom blocks, deployment, scaling
• Troubleshooting - Common issues, debugging

Resources

• Documentation: https://docs.agpt.co
• Repository: https://github.com/Significant-Gravitas/AutoGPT
• Discord: https://discord.gg/autogpt
• License: MIT (Classic) / Polyform Shield (Platform)