### Launch OpenClaw

Source: https://docs.ollama.com/integrations/openclaw

Launches OpenClaw, handling installation, security prompts, model selection, and gateway setup automatically. This is the recommended starting point.

```bash
ollama launch openclaw

```

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

### Quick Ollama Droid Setup

Source: https://docs.ollama.com/integrations/droid

Launches Droid with Ollama using a simple command. This is the fastest way to get started.

```bash
ollama launch droid
```

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

### Manual Hermes Installation

Source: https://docs.ollama.com/integrations/hermes

Install Hermes directly by running the setup wizard via curl.

```shellscript
curl -fsSL
```

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

### Python: Install Ollama SDK

Source: https://docs.ollama.com/llms-full.txt

Install the Ollama Python SDK using pip or uv. This is a prerequisite for using the Python code examples.

```bash
# with pip
pip install ollama -U

# with uv
uv add ollama
```

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

### Manual Setup for Oh My Pi with Ollama

Source: https://docs.ollama.com/integrations/oh-my-pi

After installing Oh My Pi from omp.sh, use this command to launch it with Ollama integration, which prompts for configuration.

```bash
ollama launch omp --config
```

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

### Hermes Setup Options

Source: https://docs.ollama.com/integrations/hermes

When setting up Hermes, you can choose between a quick setup or a full configuration. The quick setup is recommended for most users.

```text
How would you like to set up Hermes?

 → Quick setup — provider, model & messaging (recommended)
 Full setup — configure everything
```

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

### Launch Pi with Ollama

Source: https://docs.ollama.com/integrations/pi

Installs Pi, configures Ollama as a provider, and starts an interactive session. Use the --config flag to configure without launching.

```bash
ollama launch pi
```

```bash
ollama launch pi --config
```

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

### Launch Pi with Ollama

Source: https://docs.ollama.com/integrations/pi

This command installs Pi if needed, configures Ollama as a provider, and starts an interactive session.

```shellscript
ollama launch pi
```

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

### Install Pi

Source: https://docs.ollama.com/integrations/pi

Install Pi using the provided shell command. This is the initial step for setting up Pi.

```shellscript
ollama run pi
```

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

### Launch Applications with GPT-OSS Model

Source: https://ollama.com/library/gpt-oss

Examples of launching various applications using the GPT-OSS model. These commands assume Ollama is installed and the model is available.

```bash
ollama launch claude --model gpt-oss
```

```bash
ollama launch codex-app --model gpt-oss
```

```bash
ollama launch openclaw --model gpt-oss
```

```bash
ollama launch hermes --model gpt-oss
```

```bash
ollama launch codex --model gpt-oss
```

```bash
ollama launch opencode --model gpt-oss
```

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

### Quick Setup: Configure Ollama for Codex without Launching

Source: https://docs.ollama.com/integrations/codex

Opens the configuration for Ollama's Codex profile without immediately launching the application. Use this to modify settings before starting.

```bash
ollama launch codex --config
```

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

### Manual Hermes Installation

Source: https://docs.ollama.com/integrations/hermes

Install Hermes directly by downloading and executing the installation script. This bypasses the default `ollama launch hermes` command.

```shellscript
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
```

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

### Install Pi Agent

Source: https://docs.ollama.com/integrations/pi

Install the Pi agent using the provided shell command. This is the initial step for setting up the agent.

```shellscript
curl -fsSL https://pi.ai/install.sh | bash
```

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

### Enable and start Ollama service

Source: https://docs.ollama.com/llms-full.txt

Reload systemd, enable the Ollama service to start on boot, and start it immediately.

```shell
sudo systemctl daemon-reload
sudo systemctl enable ollama
```

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

### Launch Oh My Pi with Ollama Default Configuration

Source: https://docs.ollama.com/integrations/oh-my-pi

This command launches Oh My Pi, configuring Ollama as the model provider and enabling web search tools. It's the quickest way to get started.

```bash
ollama launch omp
```

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

### Install OpenCode CLI

Source: https://docs.ollama.com/integrations/opencode

Use this command to install the OpenCode CLI. Ensure you have curl installed.

```bash
curl -fsSL https://opencode.ai/install | bash
```

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

### Install Cline CLI

Source: https://docs.ollama.com/integrations/cline-cli

Install the Cline CLI globally using npm. If npm is available, `ollama launch cline` will prompt for installation.

```bash
npm install -g cline
```

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

### Install Marimo with uvx for Sandboxing

Source: https://docs.ollama.com/integrations/marimo

Installs Marimo and creates a sandboxed environment for running notebooks using uvx.

```bash
uvx marimo edit --sandbox notebook.py
```

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

### Install Pool

Source: https://docs.ollama.com/integrations/pool

Install the Pool software agent from its GitHub repository.

```bash
ollama launch pool
```

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

### Install Copilot CLI using npm

Source: https://docs.ollama.com/integrations/copilot-cli

Install Copilot CLI globally on any platform using npm.

```shellscript
npm install -g @github/copilot
```

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

### Install Copilot CLI using a script

Source: https://docs.ollama.com/integrations/copilot-cli

Install Copilot CLI on macOS or Linux by downloading and executing an installation script.

```shellscript
curl -fsSL https://gh.io/copilot-install | bash
```

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

### Install Copilot CLI with Homebrew

Source: https://docs.ollama.com/integrations/copilot-cli

Install Copilot CLI on macOS or Linux using Homebrew.

```bash
brew install copilot-cli
```

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

### Start Ollama Serve

Source: https://docs.ollama.com/llms-full.txt

Start the Ollama server process. This command makes Ollama available for use by other applications.

```bash
ollama serve
```

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

### Install Marimo with pip

Source: https://docs.ollama.com/llms-full.txt

Install the Marimo data notebook library using pip. This is a prerequisite for using Marimo.

```bash
pip install marimo
```

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

### Quick Ollama Setup for Claude Code

Source: https://docs.ollama.com/integrations/claude-code

This command is used for a quick setup when integrating Claude Code with Ollama.

```shellscript
ollama run claude-code
```

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

### Install Copilot CLI on Windows using WinGet

Source: https://docs.ollama.com/integrations/copilot-cli

Install Copilot CLI on Windows using the WinGet package manager.

```powershell
winget install GitHub.Copilot
```

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

### JavaScript Parallel Tool Calling with Ollama

Source: https://docs.ollama.com/llms-full.txt

This JavaScript example demonstrates parallel tool calling with Ollama. It defines functions for getting temperature and conditions, sets up tool definitions, and processes tool calls to generate a final response. Ensure the 'ollama' npm package is installed.

```typescript
import ollama from 'ollama'

function getTemperature(city: string): string {
  const temperatures: { [key: string]: string } = {
    "New York": "22°C",
    "London": "15°C",
    "Tokyo": "18°C"
  }
  return temperatures[city] || "Unknown"
}

function getConditions(city: string): string {
  const conditions: { [key: string]: string } = {
    "New York": "Partly cloudy",
    "London": "Rainy",
    "Tokyo": "Sunny"
  }
  return conditions[city] || "Unknown"
}

const tools = [
  {
    type: 'function',
    function: {
      name: 'get_temperature',
      description: 'Get the current temperature for a city',
      parameters: {
        type: 'object',
        required: ['city'],
        properties: {
          city: { type: 'string', description: 'The name of the city' },
        },
      },
    },
  },
  {
    type: 'function',
    function: {
      name: 'get_conditions',
      description: 'Get the current weather conditions for a city',
      parameters: {
        type: 'object',
        required: ['city'],
        properties: {
          city: { type: 'string', description: 'The name of the city' },
        },
      },
    },
  }
]

const messages = [{ role: 'user', content: 'What are the current weather conditions and temperature in New York and London?' }]

const response = await ollama.chat({
  model: 'qwen3',
  messages,
  tools,
  think: true
})

// add the assistant message to the messages
messages.push(response.message)
if (response.message.tool_calls) {
  // process each tool call 
  for (const call of response.message.tool_calls) {
    // execute the appropriate tool
    let result: string
    if (call.function.name === 'get_temperature') {
      const args = call.function.arguments as { city: string }
      result = getTemperature(args.city)
    } else if (call.function.name === 'get_conditions') {
      const args = call.function.arguments as { city: string }
      result = getConditions(args.city)
    } else {
      result = 'Unknown tool'
    }
    // add the tool result to the messages
    messages.push({ role: 'tool', tool_name: call.function.name, content: result })
  }

  // generate the final response
  const finalResponse = await ollama.chat({ model: 'qwen3', messages, tools, think: true })
  console.log(finalResponse.message.content)
}
```

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

### Download Ollama

Source: https://docs.ollama.com/quickstart

Click the download link to get Ollama for your operating system. This is the first step to getting started.

```html
<a href="https://ollama.com/download" target="_blank" class="mint-inline-block mint-px-6 mint-py-2 mint-bg-black mint-rounded-full dark:mint-bg-neutral-700 mint-text-white mint-font-normal mint-border-none">
  <p>Download Ollama</p>
</a>
```

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

### Manual Setup with Environment Variables

Source: https://docs.ollama.com/integrations/pool

Configure Pool to connect to Ollama by setting specific environment variables for the API base URL and API key.

```bash
export POOLSIDE_STANDALONE_BASE_URL=http://localhost:11434/v1
export POOLSIDE_API_KEY=ollama
```

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

### Install Hermes Agent Manually

Source: https://docs.ollama.com/integrations/hermes

Manually install Hermes Agent using a curl script if you prefer to run its setup wizard directly instead of using 'ollama launch hermes'.

```bash
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

```

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

### JavaScript Web Search Example

Source: https://docs.ollama.com/capabilities/web-search

This JavaScript example shows how to perform a web search using Ollama. It utilizes the Ollama API to get search results, including title, URL, and content.

```javascript
const ollama = require('ollama')

async function main() {
  const response = await ollama.chat({ 
    model: 'ollama/ollama',
    messages: [
      {
        role: 'user',
        content: 'Why is the sky blue?',
      },
    ],
  })
  console.log(response.message.content)
}

main()

```

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

### Manual Setup: Set Environment Variables and Launch

Source: https://docs.ollama.com/llms-full.txt

Manually configure Claude Code by setting environment variables for authentication and the base URL, then launch it with a specified Ollama model.

```shell
ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 claude --model qwen3-coder
```

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

### API Chat Endpoint

Source: https://docs.ollama.com/quickstart

Example of how to interact with the Ollama API to get a chat response. This uses curl to send a POST request.

```shellscript
curl http://localhost:11434/api/chat -d '{
 "model": "gemma4",
 "messages": [{"role": "user", "content": "Hello!"}]
}'
```

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

### Example: Checking Open PRs with /loop

Source: https://docs.ollama.com/integrations/claude-code

This example demonstrates using the /loop command to check open pull requests every 30 minutes and summarize their status.

```text
/loop 30m Check my open PRs and summarize their status
```

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

### Quick Setup for Copilot CLI with Ollama

Source: https://docs.ollama.com/integrations/copilot-cli

Launch Copilot CLI with Ollama for a quick setup. This command will typically prompt you to select a model if one is not already configured.

```bash
ollama launch copilot
```

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

### Quick Setup for Cline CLI with Ollama

Source: https://docs.ollama.com/integrations/cline-cli

Launch Cline CLI with Ollama automatically configured as the provider, pointing to the local Ollama endpoint and selecting a default model.

```bash
ollama launch cline
```

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

### Python Web Search Example

Source: https://docs.ollama.com/capabilities/web-search

This Python snippet demonstrates how to perform a web search using the Ollama library. Ensure you have the ollama-python library installed.

```python
from ollama import Ollama

client = Ollama("http://localhost:11434")

response = client.chat(
    model="ollama/ollama",
    messages=[
        {
            "role": "user",
            "content": "Why is the sky blue?"
        }
    ],
    options={"num_predict": 100},
    stream=True,
)

for chunk in response:
    print(chunk["message"]["content"], end="", flush=True)
print()

```

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

### Launch Applications with Qwen3 Model

Source: https://ollama.com/library/qwen3

Launch various applications pre-configured to use the Qwen3 model.

```bash
ollama launch claude --model qwen3
```

```bash
ollama launch codex-app --model qwen3
```

```bash
ollama launch openclaw --model qwen3
```

```bash
ollama launch hermes --model qwen3
```

```bash
ollama launch codex --model qwen3
```

```bash
ollama launch opencode --model qwen3
```

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

### Generate Embeddings with Python Library

Source: https://ollama.com/library/all-minilm

Call the embeddings function from the Ollama Python library to get sentence embeddings. Requires the Ollama Python library to be installed.

```python
ollama.embeddings(model='all-minilm', prompt='The sky is blue because of Rayleigh scattering')
```

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

### JavaScript Web Search Example

Source: https://docs.ollama.com/capabilities/web-search

This JavaScript snippet shows how to use the Ollama library for web search functionality. Make sure the ollama-javascript library is installed.

```tsx
import { Ollama } from "ollama"

const ollama = new Ollama()

const response = await ollama.chat({
  model: "ollama/ollama",
  messages: [
    {
      role: "user",
      content: "Why is the sky blue?",
    },
  ],
  stream: true,
})

for await (const part of response) {
  process.stdout.write(part.message.content)
}

```

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

### Example: Automating Research with /loop

Source: https://docs.ollama.com/integrations/claude-code

This example shows how to use the /loop command to research AI news hourly and summarize key developments.

```text
/loop 1h Research the latest AI news and summarize key developments
```

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

### Run a Cloud Model with Ollama.js

Source: https://docs.ollama.com/cloud

Use the Ollama JavaScript library to instantiate an Ollama client and run a cloud model. This example shows basic setup and model execution.

```typescript
import { Ollama } from "ollama";

const ollama = new Ollama({
  host: "http://localhost:11434",
  // ... other options
});

const stream = ollama.chat(
  {
    model: "gpt-oss:120b-cloud",
    messages: [{ role: "user", content: "Why is the sky blue?" }],
    stream: true,
  },
  {
    on: {
      on_data: ({ message }) => {
        // do something with the stream
        process.stdout.write(message.content);
      },
    },
  }
);

await stream.done();
```

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

### Quick Setup: Launch Ollama with Codex

Source: https://docs.ollama.com/integrations/codex

Launches Ollama with a dedicated Codex profile for the current session. This automatically refreshes the model catalog.

```bash
ollama launch codex
```

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

### Configure Apt Repository for NVIDIA Container Toolkit

Source: https://docs.ollama.com/docker

These commands set up the APT repository for the NVIDIA Container Toolkit, including adding the GPG key and the repository list.

```bash
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \
    | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
curl -fsSL https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \
    | sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' \
    | sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update
```

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

### Profile-Based Setup: Ollama Launch Configuration

Source: https://docs.ollama.com/integrations/codex

Defines a persistent Codex CLI configuration for Ollama integration by creating a TOML file. This example sets the default model and provider.

```toml
model = "gpt-oss:120b"
model_provider = "ollama-launch"
model_catalog_json = "/Users/you/.codex/model.json"

[model_providers.ollama-launch]
name = "Ollama"
base_url = "http://localhost:11434/v1/"
wire_api = "responses"

```

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

### Pi Introduction

Source: https://docs.ollama.com/integrations/pi

A brief introduction to Pi as a minimal and extensible coding agent.

```mdx
Pi is a minimal and extensible coding agent.
```

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

### Example Pool Configuration

Source: https://docs.ollama.com/integrations/pool

This snippet shows how to configure the Pool API key and specify the model to use. It demonstrates setting the POOLSIDE_API_KEY environment variable and selecting a specific model like 'kimi-k2.6:cloud'.

```shell
export POOLSIDE_API_KEY=ollama pool -m kimi-k2.6:cloud
```

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

### Simple Anthropic Messages API Example in JavaScript

Source: https://docs.ollama.com/llms-full.txt

Demonstrates a basic request to the Anthropic Messages API using Ollama's compatibility layer in JavaScript. Ensure the @anthropic-ai/sdk is installed.

```javascript
import Anthropic from "@anthropic-ai/sdk";

const anthropic = new Anthropic({
  baseURL: "http://localhost:11434",
  apiKey: "ollama", // required but ignored
});

const message = await anthropic.messages.create({
  model: "qwen3-coder",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello, how are you?" }],
});

console.log(message.content[0].text);
```

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

### Simple Anthropic Messages API Example in Python

Source: https://docs.ollama.com/llms-full.txt

Demonstrates a basic request to the Anthropic Messages API using Ollama's compatibility layer in Python. Ensure the anthropic library is installed.

```python
import anthropic

client = anthropic.Anthropic(
    base_url='http://localhost:11434',
    api_key='ollama',  # required but ignored
)

message = client.messages.create(
    model='qwen3-coder',
    max_tokens=1024,
    messages=[
        {'role': 'user', 'content': 'Hello, how are you?'}
    ]
)
print(message.content[0].text)
```

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

### Launch OpenClaw with Ollama

Source: https://docs.ollama.com/integrations/openclaw

This command launches OpenClaw using Ollama. Ollama handles the installation, security prompts, model selection, and gateway setup automatically. It also enables the bundled Ollama web search.

```shellscript
ollama launch openclaw
```

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

### Install NVIDIA Container Toolkit Packages (Apt)

Source: https://docs.ollama.com/docker

Installs the NVIDIA Container Toolkit packages using APT after configuring the repository.

```bash
sudo apt-get install -y nvidia-container-toolkit
```

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

### Verify Ollama installation

Source: https://docs.ollama.com/llms-full.txt

Check the installed Ollama version to confirm the installation was successful.

```shell
ollama -v
```

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

### Hermes Gateway Setup

Source: https://docs.ollama.com/integrations/hermes

Use this command to set up the Hermes gateway. This command initiates the gateway setup process for Hermes.

```shellscript
hermes gateway setup
```

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

### Install OMP

Source: https://docs.ollama.com/integrations/oh-my-pi

This command installs Oh My Pi. Ensure you have already installed Ollama and have it running.

```shellscript
curl -fsSL https://omp.sh | sh
```

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

### Install Marimo with uv

Source: https://docs.ollama.com/llms-full.txt

Install the Marimo data notebook library using uv. This can also be used to create sandboxed environments.

```bash
uv install marimo
```

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

### Install specific Ollama version

Source: https://docs.ollama.com/llms-full.txt

Use the OLLAMA_VERSION environment variable with the install script to install a particular version.

```shell
curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.5.7 sh
```

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

### Run Copilot CLI After Manual Setup

Source: https://docs.ollama.com/integrations/copilot-cli

Execute Copilot CLI after setting the necessary environment variables for manual API connection to Ollama.

```bash
copilot
```

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

### Initialize Ollama Client and Perform Web Search

Source: https://docs.ollama.com/capabilities/web-search

Demonstrates how to create an Ollama client instance and use the webSearch function to query information from the web. The results are then logged to the console.

```javascript
const client = new Ollama();
const results = await client.webSearch("what is ollama?");
console.log(JSON.stringify(results, null, 2));
```

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

### Specify Base Model with Tag

Source: https://docs.ollama.com/llms-full.txt

Use the FROM instruction to specify the base model and its tag for creating a new model.

```shell
FROM llama3.2
```