orchestra-research/ai-research-skills

autogpt-agents

Autonomous AI agent platform for building and deploying continuous agents.

查看源码

使用方法

  1. 复制安装命令,在自己的智能体环境安装前先检查源码包。
  2. 从原始文档核对所需工具、凭据和支持的宿主。
  3. 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/orchestra-research/ai-research-skills --skill autogpt-agents

开始前需了解

  • 安装不包含模型订阅、API 额度或访问文件的权限。
  • 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

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)

bash
# Clone repository
git clone https://github.com/Significant-Gravitas/AutoGPT.git
cd AutoGPT/autogpt_platform

# Copy environment file
cp .env.example .env

# Start backend services
docker compose up -d --build

# Start frontend (in separate terminal)
cd frontend
cp .env.example .env
npm install
npm 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:

Block TypePurpose
INPUTAgent entry points
OUTPUTAgent outputs
AILLM calls, text generation
WEBHOOKExternal triggers
STANDARDGeneral operations
AGENTNested agent execution

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:

http
POST /api/v1/graphs/{graph_id}/execute
Content-Type: application/json

{
  "inputs": {
    "input_name": "value"
  }
}

Webhook trigger:

http
POST /api/v1/webhooks/{webhook_id}
Content-Type: application/json

{
  "data": "webhook payload"
}

Scheduled execution:

json
{
  "schedule": "0 */2 * * *",
  "graph_id": "graph-uuid",
  "inputs": {}
}

Monitoring execution

WebSocket updates:

javascript
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}`);
};

REST API polling:

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

Using Forge (Development)

Create custom agent

bash
# Setup forge environment
cd classic
./run setup

# Create new agent from template
./run forge create my-agent

# Start agent server
./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

python
from 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

Benchmarking agents

Run benchmarks

bash
# Run all benchmarks
./run benchmark

# Run specific category
./run benchmark --category coding

# Run with specific agent
./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:

bash
# Record new cassettes
./run benchmark --record

# Run with existing cassettes
./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:

python
class MyLLMBlock(Block):
    def execute(self, inputs):
        # Credentials are injected by the system
        credentials = self.get_credentials("openai")
        client = OpenAI(api_key=credentials.api_key)
        # ...

Supported providers

ProviderAuth TypeUse Cases
OpenAIAPI KeyLLM, embeddings
AnthropicAPI KeyClaude models
GitHubOAuthCode, repos
GoogleOAuthDrive, Gmail, Calendar
DiscordBot TokenMessaging
NotionOAuthDocuments

Deployment

Docker production setup

yaml
# 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"

Environment variables

VariablePurpose
DATABASE_URLPostgreSQL connection
REDIS_URLRedis connection
RABBITMQ_URLRabbitMQ connection
ENCRYPTION_KEYCredential encryption
SUPABASE_URLAuthentication

Generate encryption key

bash
cd autogpt_platform/backend
poetry 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:

bash
# Check container status
docker compose ps

# View logs
docker compose logs rest_server

# Restart services
docker compose restart

Database connection issues:

bash
# Run migrations
cd backend
poetry run prisma migrate deploy

Agent execution stuck:

bash
# Check RabbitMQ queue
# Visit http://localhost:15672 (guest/guest)

# Clear stuck executions
docker compose restart executor

References

  • [Advanced Usage](references/advanced-usage.md) - Custom blocks, deployment, scaling
  • [Troubleshooting](references/troubleshooting.md) - 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)

按任务相关推荐

来自同一仓库

更多 Skills

全部 Skills
orchestra-research
社区

stable-diffusion-image-generation

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

1小时安装量
2
GitHub Stars
1.5万
最近更新
10月11日
orchestra-research
社区

evaluating-cosmos-policy

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.

1小时安装量
1
GitHub Stars
1.5万
最近更新
10月11日
orchestra-research
社区

fine-tuning-openvla-oft

Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.

1小时安装量
1
GitHub Stars
1.5万
最近更新
10月11日
orchestra-research
社区

transformer-lens-interpretability

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

1小时安装量
1
GitHub Stars
1.5万
最近更新
10月11日