### Install Sim Helm Chart (Quick Start)

Source: https://github.com/simstudioai/sim/blob/main/helm/sim/README.md

Installs the Sim Helm chart from the repository root using the default configuration. This is the simplest way to get started with deploying Sim.

```bash
helm install sim ./helm/sim
```

--------------------------------

### Clone Sim Repository and Install Dependencies

Source: https://github.com/simstudioai/sim/blob/main/README.md

This sequence of commands clones the Sim project from its GitHub repository and installs the project's dependencies using the Bun package manager. This is a prerequisite for manual setup.

```bash
git clone https://github.com/simstudioai/sim.git
cd sim
bun install
```

--------------------------------

### Configure Agent Block with System and User Prompts

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/getting-started/index.mdx

This snippet details the configuration of an Agent Block within Sim Studio. It specifies the AI model to use (OpenAI GPT-4o), the system prompt for the AI's role, and how to connect the workflow's start block input to the agent's user prompt.

```Sim Studio Configuration
Agent Block Configuration:
- Model: OpenAI GPT-4o
- System Prompt: "You are a people research agent. When given a person's name, use your available search tools to find comprehensive information about them including their location, profession, educational background, and other relevant details."
- User Prompt: Connect <start.input> to this field.
```

--------------------------------

### Setup Python SDK Development Environment

Source: https://github.com/simstudioai/sim/blob/main/packages/python-sdk/README.md

Instructions for setting up a local development environment for the SimStudio Python SDK, including cloning the repository, creating a virtual environment, installing dependencies, and running tests.

```bash
cd packages/python-sdk

python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

pip install -e ".[dev]"

pytest tests/ -v
```

--------------------------------

### Start Sim with CPU and Setup Profiles (Docker)

Source: https://github.com/simstudioai/sim/blob/main/README.md

This command starts the Sim application using Docker Compose with specific profiles for CPU-only systems and initial setup. It ensures the necessary services are running in detached mode.

```bash
docker compose -f docker-compose.ollama.yml --profile cpu --profile setup up -d
```

--------------------------------

### Add Exa and Linkup Tools to Agent Block

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/getting-started/index.mdx

This configuration shows how to enhance an AI agent's capabilities by adding external tools. It involves selecting specific tools like Exa and Linkup from the available options and providing the necessary API keys for their functionality.

```Sim Studio Configuration
Agent Block Tools Configuration:
- Add Tool: Exa
- Add Tool: Linkup
- API Keys: Provide API keys for Exa and Linkup.
```

--------------------------------

### Run Development Server (Bash)

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/README.md

This command starts the development server for the Next.js application. It requires Bun to be installed.

```bash
bun run dev
```

--------------------------------

### Starter Block Example: Manual Start

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/yaml/blocks/starter.mdx

Provides a YAML example of a Starter block configured for a manual workflow trigger. It includes the basic 'type', 'name', and 'connections' properties.

```yaml
start:
  type: starter
  name: Start
  inputs:
    startWorkflow: manual
  connections:
    success: next-block
```

--------------------------------

### Starter Block Example: Manual Start with Input Format

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/yaml/blocks/starter.mdx

Demonstrates a Starter block configured for manual triggering, including a defined 'inputFormat' to specify the expected structure for API call inputs.

```yaml
start:
  type: starter
  name: Start
  inputs:
    startWorkflow: manual
    inputFormat:
      - name: query
        type: string
      - name: email
        type: string
      - name: age
        type: number
      - name: isActive
        type: boolean
      - name: preferences
        type: object
      - name: tags
        type: array
  connections:
    success: agent-1
```

--------------------------------

### Import UI Components for Sim Studio AI

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/getting-started/index.mdx

Imports various UI components from 'fumadocs-ui' and custom components for building AI workflows in Sim Studio AI. These components include callouts, cards, file explorers, steps, tabs, theme images, and various AI/tool icons.

```TypeScript
import { Callout } from 'fumadocs-ui/components/callout'
import { Card, Cards } from 'fumadocs-ui/components/card'
import { File, Files, Folder } from 'fumadocs-ui/components/files'
import { Step, Steps } from 'fumadocs-ui/components/steps'
import { Tab, Tabs } from 'fumadocs-ui/components/tabs'
import { ThemeImage } from '@/components/ui/theme-image'
import {
  AgentIcon,
  ApiIcon,
  ChartBarIcon,
  CodeIcon,
  ConditionalIcon,
  ConnectIcon,
  ExaAIIcon,
  FirecrawlIcon,
  GmailIcon,
  NotionIcon,
  PerplexityIcon,
  SlackIcon,
} from '@/components/icons'
import { Video } from '@/components/ui/video'
```

--------------------------------

### Generate JSON Schema for Structured Output

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/getting-started/index.mdx

This process demonstrates how to configure an Agent Block to return structured data. It involves using an AI prompt to automatically generate a JSON schema based on specified fields like location, profession, and education.

```Sim Studio Configuration
Agent Block Response Format Configuration:
- Click the magic wand icon next to the schema field.
- Prompt AI: "create a schema named person, that contains location, profession, and education"
```

--------------------------------

### Install Sim Python SDK

Source: https://github.com/simstudioai/sim/blob/main/packages/python-sdk/README.md

Installs the Sim Python SDK using pip. This is the first step to using the SDK in your Python projects.

```bash
pip install simstudio-sdk
```

--------------------------------

### Basic Workflow Execution Example

Source: https://github.com/simstudioai/sim/blob/main/packages/python-sdk/README.md

A comprehensive example demonstrating how to initialize the client, validate a workflow, execute it with input data, and handle the results or errors.

```python
import os
from simstudio import SimStudioClient

client = SimStudioClient(api_key=os.getenv("SIMSTUDIO_API_KEY"))

def run_workflow():
    try:
        # Check if workflow is ready
        is_ready = client.validate_workflow("my-workflow-id")
        if not is_ready:
            raise Exception("Workflow is not deployed or ready")

        # Execute the workflow
        result = client.execute_workflow(
            "my-workflow-id",
            input_data={
                "message": "Process this data",
                "user_id": "12345"
            }
        )

        if result.success:
            print("Output:", result.output)
            print("Duration:", result.metadata.get("duration") if result.metadata else None)
        else:
            print("Workflow failed:", result.error)
            
    except Exception as error:
        print("Error:", error)

run_workflow()
```

--------------------------------

### Run Python SDK Examples

Source: https://github.com/simstudioai/sim/blob/main/packages/README.md

Instructions to run example scripts for the Python SDK, setting the API key environment variable.

```Bash
cd packages/python-sdk
SIMSTUDIO_API_KEY=your-key python examples/basic_usage.py
```

--------------------------------

### Install Sim TypeScript SDK

Source: https://github.com/simstudioai/sim/blob/main/packages/ts-sdk/README.md

Instructions for installing the Sim TypeScript SDK using npm, yarn, or bun.

```bash
npm install simstudio-ts-sdk
# or 
yarn add simstudio-ts-sdk
# or
bun add simstudio-ts-sdk
```

--------------------------------

### Run TypeScript SDK Examples

Source: https://github.com/simstudioai/sim/blob/main/packages/README.md

Instructions to run example scripts for the TypeScript SDK, setting the API key environment variable.

```Bash
cd packages/ts-sdk
SIMSTUDIO_API_KEY=your-key bun run examples/basic-usage.ts
```

--------------------------------

### Self-host Sim.ai with Docker Compose

Source: https://github.com/simstudioai/sim/blob/main/README.md

This set of commands outlines the process for self-hosting Sim.ai using Docker Compose. It involves cloning the Sim.ai repository, navigating into the project directory, and then starting the application in detached mode using a production-specific Docker Compose file. Docker must be installed and running.

```bash
# Clone the repository
git clone https://github.com/simstudioai/sim.git

# Navigate to the project directory
cd sim

# Start Sim
docker compose -f docker-compose.prod.yml up -d
```

--------------------------------

### Web Search with Structured Output

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/yaml/examples.mdx

This workflow searches the web using tools and returns structured data. It utilizes an agent with a system prompt to guide the search and specifies a tool (Exa) for web searching. The response format is defined using a JSON schema.

```yaml
version: '1.0'
blocks:
  59eb07c1-1411-4b28-a274-fa78f55daf72:
    type: starter
    name: Start
    inputs:
      startWorkflow: manual
    connections:
      success: d77c2c98-56c4-432d-9338-9bac54a2d42f
  d77c2c98-56c4-432d-9338-9bac54a2d42f:
    type: agent
    name: Agent 1
    inputs:
      systemPrompt: look up the user input. use structured output
      userPrompt: <start.input>
      model: claude-sonnet-4-0
      apiKey: '{{ANTHROPIC_API_KEY}}'
      tools:
        - type: exa
          title: Exa
          params:
            type: auto
            apiKey: '{{EXA_API_KEY}}'
            numResults: ''
          toolId: exa_search
          operation: exa_search
          isExpanded: true
          usageControl: auto
      responseFormat: |-
        {
            "name": "output_schema",
            "description": "Defines the structure for an output object.",
            "strict": true,
            "schema": {
                "type": "object",
                "properties": {
                    "output": {
                        "type": "string",
                        "description": "The output value"
                    }
                },
                "additionalProperties": false,
                "required": ["output"]
            }
        }
```

--------------------------------

### Install Sim CLI Globally

Source: https://github.com/simstudioai/sim/blob/main/packages/cli/README.md

Installs the Sim CLI globally using npm. This command makes the 'simstudio' executable available in your system's PATH.

```bash
npm install -g simstudio
```

--------------------------------

### Start Sim Next.js Application

Source: https://github.com/simstudioai/sim/blob/main/README.md

This command starts only the Next.js application for Sim from the project root. It's an alternative if only the main application needs to be run.

```bash
bun run dev
```

--------------------------------

### Install Sim SDKs (TypeScript/JavaScript & Python)

Source: https://github.com/simstudioai/sim/blob/main/packages/README.md

Commands to install the Sim Studio SDKs for TypeScript/JavaScript using npm, yarn, or bun, and for Python using pip.

```Bash
npm install simstudio-ts-sdk
```

```Bash
yarn add simstudio-ts-sdk
```

```Bash
bun add simstudio-ts-sdk
```

```Bash
pip install simstudio-sdk
```

--------------------------------

### Basic Workflow Execution Example

Source: https://github.com/simstudioai/sim/blob/main/packages/ts-sdk/README.md

A comprehensive example demonstrating the workflow execution process, including validating readiness, executing the workflow with input, and handling the results or errors.

```typescript
import { SimStudioClient } from 'simstudio-ts-sdk';

const client = new SimStudioClient({
  apiKey: process.env.SIMSTUDIO_API_KEY!
});

async function runWorkflow() {
  try {
    // Check if workflow is ready
    const isReady = await client.validateWorkflow('my-workflow-id');
    if (!isReady) {
      throw new Error('Workflow is not deployed or ready');
    }

    // Execute the workflow
    const result = await client.executeWorkflow('my-workflow-id', {
      input: {
        message: 'Process this data',
        userId: '12345'
      }
    });

    if (result.success) {
      console.log('Output:', result.output);
      console.log('Duration:', result.metadata?.duration);
    } else {
      console.error('Workflow failed:', result.error);
    }
  } catch (error) {
    console.error('Error:', error);
  }
}

runWorkflow();
```

--------------------------------

### Start Sim Realtime Socket Server

Source: https://github.com/simstudioai/sim/blob/main/README.md

This command starts the realtime socket server for Sim. It needs to be executed from the apps/sim directory in a separate terminal, complementing the Next.js application.

```bash
cd apps/sim
bun run dev:sockets
```

--------------------------------

### Install Dependencies with Bun

Source: https://github.com/simstudioai/sim/blob/main/packages/ts-sdk/README.md

Command to install project dependencies using the Bun package manager. This is a common step after cloning a repository or setting up a new project.

```bash
bun install
```

--------------------------------

### Install Sim for GCP Environment (GKE)

Source: https://github.com/simstudioai/sim/blob/main/helm/sim/README.md

Deploys Sim optimized for Google Kubernetes Engine (GKE) using the `values-gcp.yaml` configuration. It installs into the `simstudio` namespace.

```bash
helm install sim-gcp ./helm/sim \
  --values ./helm/sim/examples/values-gcp.yaml \
  --namespace simstudio --create-namespace
```

--------------------------------

### Example: Simple GET Request with Headers

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/yaml/blocks/api.mdx

This example demonstrates a simple GET request to fetch user data. It includes setting an 'Authorization' header with a Bearer token and a 'Content-Type' header. The connections specify the next block for success and error scenarios.

```yaml
user-api:
  type: api
  name: "Fetch User Data"
  inputs:
    url: "https://api.example.com/users/123"
    method: GET
    headers:
      - id: header-1-uuid-here
        cells:
          Key: "Authorization"
          Value: "Bearer {{API_TOKEN}}"
      - id: header-2-uuid-here
        cells:
          Key: "Content-Type"
          Value: "application/json"
  connections:
    success: process-user-data
    error: handle-api-error
```

--------------------------------

### Example: Dynamic URL with Query Parameters

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/yaml/blocks/api.mdx

This example illustrates a GET request to search products, utilizing dynamic query parameters for search terms and category. It also includes an 'Authorization' header and sets a fixed limit parameter. The connections specify the next block for displaying results.

```yaml
search-api:
  type: api
  name: "Search Products"
  inputs:
    url: "https://api.store.com/products"
    method: GET
    params:
      - id: search-param-uuid
        cells:
          Key: "q"
          Value: <start.searchTerm>
      - id: limit-param-uuid
        cells:
          Key: "limit"
          Value: "10"
      - id: category-param-uuid
        cells:
          Key: "category"
          Value: <filter.category>
    headers:
      - id: auth-header-uuid
        cells:
          Key: "Authorization"
          Value: "Bearer {{STORE_API_KEY}}"
  connections:
    success: display-results
```

--------------------------------

### Setup Documentation Generator Dependencies

Source: https://github.com/simstudioai/sim/blob/main/scripts/README.md

Installs necessary dependencies for the documentation generator, including TypeScript, ts-node, and type definitions. This script resolves common TypeScript and module resolution errors.

```bash
#!/bin/bash
./scripts/setup-doc-generator.sh
```

--------------------------------

### Start Sim Development Servers (Full Stack)

Source: https://github.com/simstudioai/sim/blob/main/README.md

This command starts both the main Next.js application and the realtime socket server for the Sim project from the project root. It's the recommended approach for a complete development environment.

```bash
bun run dev:full
```

--------------------------------

### Self-host Sim.ai with Docker Compose and Ollama

Source: https://github.com/simstudioai/sim/blob/main/README.md

This command demonstrates how to self-host Sim.ai using Docker Compose, specifically configured to utilize local AI models through Ollama. It starts the application with GPU support and automatically downloads the 'gemma3:4b' model. Docker and Ollama must be installed and running.

```bash
# Start with GPU support (automatically downloads gemma3:4b model)
docker compose -f docker-compose.ollama.yml --profile setup up -d
```

--------------------------------

### Count-Based Parallel Processing Example - YAML

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/yaml/blocks/parallel.mdx

This YAML configuration shows a 'count'-based parallel block named 'Worker Parallel'. It specifies 5 parallel instances with a maximum concurrency of 3, defining the start task ('worker-task') and an optional end task ('collect-worker-results').

```yaml
worker-parallel:
  type: parallel
  name: "Worker Parallel"
  inputs:
    parallelType: count
    count: 5
    maxConcurrency: 3
  connections:
    parallel:
      start: worker-task
      end: collect-worker-results

worker-task:
  type: api
  name: "Worker Task"
  parentId: worker-parallel
  inputs:
    url: "https://api.worker.com/process"
    method: POST
    headers:
      - key: "Authorization"
        value: "Bearer {{WORKER_API_KEY}}"
    body: |
      {
        "instanceId": <parallel.index>,
        "timestamp": "{{new Date().toISOString()}}"
      }
  connections:
    success: worker-complete
```

--------------------------------

### Configure SimStudioClient with Environment Variables in Python

Source: https://github.com/simstudioai/sim/blob/main/packages/python-sdk/README.md

Illustrates how to initialize the SimStudioClient by reading the API key and base URL from environment variables, providing flexibility in configuration.

```python
import os
from simstudio import SimStudioClient

# Using environment variables
client = SimStudioClient(
    api_key=os.getenv("SIMSTUDIO_API_KEY"),
    base_url=os.getenv("SIMSTUDIO_BASE_URL", "https://sim.ai")
)
```

--------------------------------

### Starter API Execution - Manual Mode (Bash)

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/triggers/starter.mdx

Provides a cURL command to initiate a workflow via the API in Manual Mode, sending structured parameters.

```bash
curl -X POST "https://api.sim.dev/v1/workflows/{id}/start" \
  -H "Authorization: Bearer {api-key}" \
  -d '{"parameters": {"userId": "123", "action": "process"}}'
```

--------------------------------

### Initialize SimStudioClient

Source: https://github.com/simstudioai/sim/blob/main/packages/python-sdk/README.md

Initializes the SimStudioClient with an API key and an optional base URL. The API key can be fetched from environment variables.

```python
import os
from simstudio import SimStudioClient

client = SimStudioClient(
    api_key=os.getenv("SIMSTUDIO_API_KEY", "your-api-key-here"),
    base_url="https://sim.ai"  # optional, defaults to https://sim.ai
)
```

--------------------------------

### Multi-Agent Chain Workflow Example

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/yaml/examples.mdx

Demonstrates a sequential workflow where multiple AI agents process information. Each agent builds upon the output of the previous one, culminating in a final refined output. This example uses the 'agent' block type and specifies prompts, models, and API keys.

```yaml
version: '1.0'
blocks:
  start:
    type: starter
    name: Start
    inputs:
      startWorkflow: manual
    connections:
      success: agent-1-initiator

  agent-1-initiator:
    type: agent
    name: Agent 1 Initiator
    inputs:
      systemPrompt: You are the first agent in a chain. Your role is to analyze the input and create an initial response that will be passed to the next agent.
      userPrompt: |-
        Welcome! I'm the first agent in our chain.

        Input to process: <start.input>

        Please create an initial analysis or greeting that the next agent can build upon. Be creative and set a positive tone for the chain!
      model: gpt-4o
      temperature: 0.7
      apiKey: '{{OPENAI_API_KEY}}'
    connections:
      success: agent-2-enhancer

  agent-2-enhancer:
    type: agent
    name: Agent 2 Enhancer
    inputs:
      systemPrompt: You are the second agent in a chain. Take the output from Agent 1 and enhance it with additional insights or improvements.
      userPrompt: |-
        I'm the second agent! Here's what Agent 1 provided:

        <agent1initiator.content>

        Now I'll enhance this with additional details, insights, or improvements. Let me build upon their work!
      model: gpt-4o
      temperature: 0.7
      apiKey: '{{OPENAI_API_KEY}}'
    connections:
      success: agent-3-refiner

  agent-3-refiner:
    type: agent
    name: Agent 3 Refiner
    inputs:
      systemPrompt: You are the third agent in a chain. Take the enhanced output from Agent 2 and refine it further, adding structure or organization.
      userPrompt: |-
        I'm the third agent in our chain! Here's the enhanced work from Agent 3:

        <agent2enhancer.content>

        My job is to refine and organize this content. I'll add structure, clarity, and polish to make it even better!
      model: gpt-4o
      temperature: 0.6
      apiKey: '{{OPENAI_API_KEY}}'
    connections:
      success: agent-4-finalizer

  agent-4-finalizer:
    type: agent
    name: Agent 4 Finalizer
    inputs:
      systemPrompt: You are the final agent in a chain of 4. Create a comprehensive summary and conclusion based on all the previous agents' work.
      userPrompt: |-
        I'm the final agent! Here's the refined work from Agent 3:

        <agent3refiner.content>

        As the last agent in our chain, I'll create a final, polished summary that brings together all the work from our team of 4 agents. Let me conclude this beautifully!
      model: gpt-4o
      temperature: 0.5
      apiKey: '{{OPENAI_API_KEY}}'

```

--------------------------------

### Starter Block Example: Weekly Schedule

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/yaml/blocks/starter.mdx

Presents a YAML example of a Starter block configured for a weekly schedule. It includes 'scheduleType', 'weeklyDay', 'weeklyTime', and 'timezone' for precise scheduling.

```yaml
start:
  type: starter
  name: Start
  inputs:
    startWorkflow: schedule
    scheduleType: weekly
    weeklyDay: MON
    weeklyTime: "08:30"
    timezone: UTC
  connections:
    success: weekly-report
```

--------------------------------

### Install Sim for Production Environment

Source: https://github.com/simstudioai/sim/blob/main/helm/sim/README.md

Deploys Sim in a production environment using the `values-production.yaml` configuration file. It targets the `simstudio-prod` namespace and ensures its creation.

```bash
helm install sim-prod ./helm/sim \
  --values ./helm/sim/examples/values-production.yaml \
  --namespace simstudio-prod --create-namespace
```

--------------------------------

### Starter API Execution - Chat Mode (Bash)

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/triggers/starter.mdx

Provides a cURL command to initiate a workflow via the API in Chat Mode, sending natural language input.

```bash
curl -X POST "https://api.sim.dev/v1/workflows/{id}/start" \
  -H "Authorization: Bearer {api-key}" \
  -d '{"input": "Analyze Q4 sales data"}'
```

--------------------------------

### Object Variable Example

Source: https://github.com/simstudioai/sim/blob/main/apps/docs/content/docs/variables/index.mdx

Provides an example of storing structured data with properties and values as an object variable. Uses JSON format.

```json
{
  "name": "John",
  "age": 30,
  "city": "New York"
}
```