Integrations

ChatGPT Desktop
Claude Code
Claude Desktop
Cline CLI
Cline
Codex CLI
Copilot CLI
DeepSeek Harness
Droid
Goose
Hermes Desktop
Hermes Agent
Overview
JetBrains
marimo
n8n
NemoClaw
Oh My Pi
Onyx
OpenClaw
OpenCode
Pi
Pool
Roo Code
VS Code
Xcode
Zed

ChatGPT Desktop

ChatGPT Desktop includes Codex, OpenAI's desktop coding agent. Ollama adds compatible local and cloud models to Codex's model picker alongside ChatGPT's native models.

Prerequisites

Ollama v0.34.0 or newer

If ChatGPT is not installed, Ollama offers to download it during setup.

Connect ChatGPT

Open the Ollama desktop app and select Apps.
Toggle ChatGPT (Desktop) to On.
Follow the setup prompts. If ChatGPT is already open, Ollama asks to restart it before the new models appear.
Open the ChatGPT desktop app and use Codex mode.

Choose models

Open Ollama Settings, select Apps, then select ChatGPT. Choose up to five compatible local or cloud models and save your changes. Ollama asks to restart ChatGPT when a model change needs one.

Disconnect ChatGPT

Open Ollama Apps and turn ChatGPT off. Ollama restores ChatGPT's connection settings and usual profile. If ChatGPT is open, Ollama asks to restart it so the change takes effect.

Codex behavior and limits

Only requests made with an Ollama model go to Ollama. ChatGPT's native models keep using their usual provider.
Ollama models are for Codex mode. Regular Chat and voice keep using their usual ChatGPT connection.
Codex manages sessions. Ollama routes model requests and compaction when Codex asks for it, but does not store ChatGPT sessions.
Web search uses Ollama's web-search service when you use an Ollama model. It requires Ollama sign-in and is limited to three calls per response.

Use Codex from a terminal with Codex CLI.
Connect other desktop apps from Claude Desktop.

Claude Code

Claude Code reads your codebase, edits files, and runs commands.

Ollama connects Claude Code to local and cloud models through its Anthropic-compatible API.

Get started

Launch Claude Code with Ollama:

ollama launch claude

Capabilities

Chat

Ask questions about a repository or task

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="terminal" /></div>
  <div>
    <div className="capability-list-heading">Command line</div>
    <div className="capability-list-copy">Run commands with Claude Code's permission flow</div>
  </div>
</div>

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="code" /></div>
  <div>
    <div className="capability-list-heading">Tool calling</div>
    <div className="capability-list-copy">Use tools with compatible models</div>
  </div>
</div>

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="file-pen" /></div>
  <div>
    <div className="capability-list-heading">File edits</div>
    <div className="capability-list-copy">Read and edit files in your project</div>
  </div>
</div>

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="users" /></div>
  <div>
    <div className="capability-list-heading">Subagents</div>
    <div className="capability-list-copy">Split work across tasks</div>
  </div>
</div>

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="globe" /></div>
  <div>
    <div className="capability-list-heading">Web search</div>
    <div className="capability-list-copy">Search the web through Ollama</div>
  </div>
</div>

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="file-text" /></div>
  <div>
    <div className="capability-list-heading">Web fetch</div>
    <div className="capability-list-copy">Fetch and summarize web pages</div>
  </div>
</div>

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="image" /></div>
  <div>
    <div className="capability-list-heading">Vision</div>
    <div className="capability-list-copy">Send images and screenshots</div>
  </div>
</div>

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="brain" /></div>
  <div>
    <div className="capability-list-heading">Thinking</div>
    <div className="capability-list-copy">Use thinking controls with compatible models</div>
  </div>
</div>

Models

Choose a model with enough context for your repository.

Use larger models without downloading them. Choose a model and set a 64k+ context window.

For larger repositories, set the context length to 64k or higher.

More features

Run without interaction

Use --yes for scripts, Docker, or CI:

ollama launch claude --model gemma4:cloud --yes -- -p "how does this repository work?"

The --yes flag skips selectors, pulls the model when needed, and requires --model. Arguments after -- are passed directly to Claude Code.

Web search

Use Ollama's web search API from Claude Code.

See Web search for setup and usage.

Scheduled tasks with `/loop`

Use /loop inside Claude Code to run a prompt or slash command on a schedule:

/loop <interval> <prompt or /command>

Examples:

/loop 30m Check my open PRs and summarize their status
/loop 1h Research the latest AI news and summarize key developments
/loop 15m Check for new GitHub issues and triage by priority

Connect a Telegram bot to your Claude Code session. Install the Telegram plugin, create a bot with @BotFather, then launch Claude Code:

ollama launch claude -- --channels plugin:telegram@claude-plugins-official

Claude Code prompts for permission on most actions. To allow the bot to work autonomously, configure permission rules or pass --dangerously-skip-permissions in an isolated environment.

See the plugin README for setup instructions.

Connect directly to Ollama's cloud

Install Claude Code, then set your API key in OLLAMA_API_KEY. No Ollama installation required.

In Bash or Zsh, run:

ANTHROPIC_BASE_URL=https://ollama.com \
ANTHROPIC_AUTH_TOKEN="$OLLAMA_API_KEY" \
ANTHROPIC_API_KEY="" \
claude --model glm-5.3-flash

Use ANTHROPIC_AUTH_TOKEN for bearer authentication. Claude settings can override shell variables. Update any base URL or credentials in those settings, then run /status to check the connection.

Choose a cloud model that supports tools. Basic chat and file edits work with compatible models. Hosted WebSearch and advanced tool controls are not fully supported. See Anthropic compatibility.

Manual setup

1. Install Claude Code

curl -fsSL https://claude.ai/install.sh | bash

irm https://claude.ai/install.ps1 | iex

2. Set the environment variables

export ANTHROPIC_AUTH_TOKEN=ollama
export ANTHROPIC_API_KEY=""
export ANTHROPIC_BASE_URL=http://localhost:11434

3. Run Claude Code

claude --model qwen3.5

Or run with environment variables inline:

ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 ANTHROPIC_API_KEY="" claude --model kimi-k2.7-code:cloud

Claude Desktop

Ollama. Windows support coming soon.
To use a local model, download it before setup.
To use a cloud model, sign in to Ollama and enable cloud models. Some models require a paid plan.

If Claude is not installed, Ollama offers to download it during setup.

Set up Claude

Open Ollama and select Apps.
Connect Claude.
Follow the setup prompts to install Claude if needed and restart it when prompted.

Switch models

Open Ollama Settings → Apps. Choose your models, then select Restart Claude. You can use the same model for more than one option.

Supported features

Subagents - Split larger tasks across agents
Web search - Supported by default through Ollama's web search
Cowork - Complete difficult tasks with Claude Cowork
Auto mode - Let the agent decide when to ask before making changes

Disconnect Claude

Open Ollama Apps and disconnect Claude. Ollama restores Claude's previous settings. Restart Claude when prompted.

You can also restore Claude from the terminal:

ollama launch claude-desktop --restore

Quitting Ollama while Claude is connected also restores Claude's usual configuration.

Cline CLI

Cline CLI is an autonomous coding agent for interactive terminal sessions.

Install

Install the Cline CLI. For the IDE extension, see Cline.

npm install -g cline

If Cline CLI is not installed and npm is available, ollama launch cline will prompt to install cline@latest.

Usage with Ollama

Quick setup

ollama launch cline

When launched through ollama launch cline, Ollama sets Cline's provider to Ollama, points it at the local Ollama endpoint, and selects the model you choose.

To configure without launching:

ollama launch cline --config

Run directly with a model

ollama launch cline --model qwen3.5

To use a cloud model:

ollama launch cline --model kimi-k2.6:cloud

Pass a prompt to Cline

Arguments after -- are passed directly to Cline:

ollama launch cline -- "summarize this repository"

To open Cline's Kanban board:

ollama launch cline -- kanban

Manual setup

To configure Cline CLI manually, first make sure Ollama is running and the model you want to use is available:

ollama pull qwen3.5

Then run Cline's interactive auth flow:

cline auth

Select Ollama as the provider, use http://localhost:11434 as the base URL if prompted, and choose a model such as qwen3.5 or kimi-k2.6:cloud.

To check the current Cline configuration:

cline config

To start an interactive session:

cline

Cline

Install Cline in your IDE.

Usage with Ollama

Open Cline settings > API Configuration and set API Provider to Ollama
Select a model under Model or type one (e.g. qwen3)
Update the context window to at least 32K tokens under Context Window

Use a context window of at least 32K tokens for coding.

Cline settings configuration showing API Provider set to Ollama

Connecting to ollama.com

Create an API key from ollama.com
Click on Use custom base URL and set it to https://ollama.com
Enter your Ollama API Key
Select a model from the list

Models

Choose a cloud model that supports tool calling.

Codex CLI

Install the Codex CLI. For the ChatGPT desktop app, see ChatGPT Desktop.

npm install -g @openai/codex

Usage with Ollama

Use a context window of at least 64k tokens for Codex.

Quick setup

ollama launch codex

When launched through ollama launch codex, Ollama refreshes the model catalog and uses a dedicated Codex profile for that session.

Type /model inside Codex to switch between your installed, tool-capable Ollama models without restarting. The starting model remains selected, and each model keeps its own context window, vision, and thinking settings. Pull additional models with ollama pull <model> before launching to include them in the picker.

To configure without launching:

ollama launch codex --config

To remove the Ollama launch profile and generated model catalog:

ollama launch codex --restore

Manual setup

To use codex with Ollama, use the --oss flag:

codex --oss

To use a specific model, pass the -m flag:

codex --oss -m gpt-oss:120b

To use a cloud model:

codex --oss -m gpt-oss:120b-cloud

Profile-based setup

For a persistent Codex CLI configuration, create ~/.codex/ollama-launch.config.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"

Then run:

codex --profile ollama-launch

Web search through local Ollama

Codex web-search requests sent through the Ollama profile are executed by Ollama for both local and cloud models. Sign in with ollama signin to use the web-search service.

To disable web search for a Codex session:

codex --profile ollama-launch -c 'web_search="disabled"'

Copilot CLI

GitHub Copilot CLI is GitHub's AI coding agent for the terminal. It can understand your codebase, make edits, run commands, and help you build software faster.

Open models can be used with Copilot CLI through Ollama, enabling you to use models such as qwen3.5, glm-5.3:cloud, kimi-k3:cloud See all supported models here.

Install

Install Copilot CLI:

brew install copilot-cli

npm install -g @github/copilot

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

winget install GitHub.Copilot

Usage with Ollama

Quick setup

ollama launch copilot

Run directly with a model

ollama launch copilot --model kimi-k2.5:cloud

Non-interactive (headless) mode

Run Copilot CLI without interaction for use in Docker, CI/CD, or scripts:

ollama launch copilot --model kimi-k2.5:cloud --yes -- -p "how does this repository work?"

The --yes flag auto-pulls the model, skips selectors, and requires --model to be specified. Arguments after -- are passed directly to Copilot CLI.

Manual setup

Copilot CLI connects to Ollama using the OpenAI-compatible API via environment variables.

Set the environment variables:

export COPILOT_PROVIDER_BASE_URL=http://localhost:11434/v1
export COPILOT_PROVIDER_API_KEY=
export COPILOT_PROVIDER_WIRE_API=responses
export COPILOT_MODEL=qwen3.5

Run Copilot CLI:

copilot

Or run with environment variables inline:

COPILOT_PROVIDER_BASE_URL=http://localhost:11434/v1 COPILOT_PROVIDER_API_KEY= COPILOT_PROVIDER_WIRE_API=responses COPILOT_MODEL=glm-5:cloud copilot

Note: Copilot requires a large context window. We recommend at least 64k tokens. See the context length documentation for how to adjust context length in Ollama.

DeepSeek Harness

DeepSeek Harness is an open-source coding agent.

DeepSeek Harness is currently a developer preview. Its upstream configuration may change between releases.

Setup

ollama launch dsh

Ollama installs @deepseek-ai/dsh if needed. To choose a model:

ollama launch dsh --model qwen3.8
ollama launch dsh --model deepseek-v4-flash:cloud

To configure without starting:

ollama launch dsh --config

Web search

Web search is enabled automatically. It requires access to Ollama's cloud and a model that supports tools. Run ollama signin if needed.

Configuration

Ollama stores its settings in ~/.ollama/launch/dsh/settings.yaml. These settings load last and set the model, provider, and web search connection. Repeated launches preserve other settings in this file. Ollama does not change ~/.dsh/settings.yaml, profiles, sessions, or credentials.

Launch rejects additional --patch arguments. Pass other Harness arguments after --:

ollama launch dsh -- --port 3081

Manual install

DeepSeek Harness requires Node.js. To install it manually:

npm install -g @deepseek-ai/dsh@latest

Then run ollama launch dsh. On Windows, install Node.js for Windows.

Droid

Install the Droid CLI:

curl -fsSL https://app.factory.ai/cli | sh

Droid requires a larger context window. It is recommended to use a context window of at least 64k tokens. See Context length for more information.

Usage with Ollama

Quick setup

ollama launch droid

To configure without launching:

ollama launch droid --config

Manual setup

Add a local configuration block to ~/.factory/config.json:

{
  "custom_models": [
    {
      "model_display_name": "qwen3-coder [Ollama]",
      "model": "qwen3-coder",
      "base_url": "http://localhost:11434/v1/",
      "api_key": "not-needed",
      "provider": "generic-chat-completion-api",
      "max_tokens": 32000 
    }
  ]
}

Cloud Models

The following example configures qwen3-coder for use with Droid.

Add the cloud configuration block to ~/.factory/config.json:

{
  "custom_models": [
    {
      "model_display_name": "qwen3-coder [Ollama's cloud]",
      "model": "qwen3-coder:480b-cloud",
      "base_url": "http://localhost:11434/v1/",
      "api_key": "not-needed",
      "provider": "generic-chat-completion-api",
      "max_tokens": 128000
    }
  ]
}

Connecting to ollama.com

Create an API key from ollama.com and export it as OLLAMA_API_KEY.

Add the cloud configuration block to ~/.factory/config.json:

{
  "custom_models": [
    {
      "model_display_name": "qwen3-coder [Ollama's cloud]",
      "model": "qwen3-coder:480b",
      "base_url": "https://ollama.com/v1/",
      "api_key": "OLLAMA_API_KEY",
      "provider": "generic-chat-completion-api",
      "max_tokens": 128000
    }
  ]
}

Run droid in a new terminal to load the new settings.

Goose

Install Goose Desktop.

Usage with Ollama

In Goose, open Settings → Configure Provider.

2. Find **Ollama**, click **Configure** 3. Confirm **API Host** is `http://localhost:11434` and click Submit

Connecting to ollama.com

Create an API key on ollama.com and save it in your .env
In Goose, set API Host to https://ollama.com

Goose CLI

Install Goose CLI

Usage with Ollama

Run goose configure
Select Configure Providers and select Ollama

3. Enter model name (e.g `qwen3`)

Connecting to ollama.com

Create an API key on ollama.com and save it in your .env
Run goose configure
Select Configure Providers and select Ollama
Update OLLAMA_HOST to https://ollama.com

Hermes Desktop

Hermes Desktop is a native AI assistant app by Nous Research. It provides a desktop chat interface for Hermes Agent, an AI agent that can work with models, run tools, manage projects, use memory and skills, and connect to messaging gateways.

Hermes Desktop with Ollama

Quick start

ollama launch hermes-desktop

Ollama handles the setup flow automatically:

Install - If Hermes isn't installed, Ollama prompts to install the Hermes command-line agent. On first desktop launch, Hermes builds its packaged desktop app.
Model - Pick a model from the selector
Configure - Ollama configures Hermes Desktop to use your selected Ollama model
Launch - Ollama opens Hermes Desktop

Run directly with a model

ollama launch hermes-desktop --model <model>

Run ollama launch hermes-desktop again to switch models later.

Install Hermes Desktop directly

On macOS and Windows, the Hermes Desktop installer is the recommended upstream installation path. It installs the desktop app and Hermes Agent together. If you prefer the command line, ollama launch hermes-desktop remains the explicit Ollama-managed path and uses the same Hermes configuration, sessions, skills, and memory as the CLI.

To force Hermes to rebuild its packaged desktop app:

ollama launch hermes-desktop -- --force-build

Hermes Agent

Hermes Agent is a self-improving AI agent built by Nous Research. It features automatic skill creation, cross-session memory, and 70+ skills that it ships with by default.

Hermes Agent with Ollama

Quick start

ollama launch hermes

Ollama handles everything automatically:

Install — If Hermes isn't installed, Ollama prompts to install the Hermes command-line agent
Model — Pick a model from the selector (local or cloud). See currently-supported models here.
Onboarding — Ollama configures the Ollama provider, points Hermes at http://127.0.0.1:11434/v1, and sets your model as the primary
Gateway — Optionally connects a messaging platform (Telegram, Discord, Slack, WhatsApp, Signal, Email) and launches the Hermes chat

Connect messaging apps

Link Telegram, Discord, Slack, WhatsApp, Signal, or Email to chat with your models from anywhere:

hermes gateway setup

Reconfigure

Use Hermes's model picker to change providers or models later:

hermes model

Manual setup

If you'd rather drive Hermes's own wizard instead of ollama launch hermes, install it directly:

curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

Hermes launches the setup wizard automatically. Choose Quick setup:

How would you like to set up Hermes?

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

Connect to Ollama

Select More providers...
Select Custom endpoint (enter URL manually)

Set the API base URL to the Ollama OpenAI-compatible endpoint:

API base URL [e.g. https://api.example.com/v1]: http://127.0.0.1:11434/v1

Leave the API key blank (not required for local Ollama):
```
API key [optional]:
```

Hermes auto-detects downloaded models, confirm the one you want:

Verified endpoint via http://127.0.0.1:11434/v1/models (1 model(s) visible)
  Detected model: kimi-k2.5:cloud
  Use this model? [Y/n]:

Leave context length blank to auto-detect:

Context length in tokens [leave blank for auto-detect]:

Connect messaging

Optionally connect a messaging platform during setup:

Connect a messaging platform? (Telegram, Discord, etc.)

 →  Set up messaging now (recommended)
    Skip — set up later with 'hermes gateway setup'

Launch

Launch hermes chat now? [Y/n]: Y

Overview

Use Ollama models in your apps and tools.

Launch a coding agent

Run ollama launch in a terminal to choose a coding agent.

Read code, edit files, and run commands. Edit and run code from your terminal. Use DeepSeek's open-source coding agent in your browser.

Connect a desktop app

On macOS, open the Ollama app and select Apps in the sidebar. Connect Claude or ChatGPT.

Use local and cloud Ollama models. Use Ollama models in Codex mode.

Run a personal assistant

Run ollama launch in a terminal and choose OpenClaw or Hermes Agent.

Chat with an assistant through your messaging apps. Personal assistant with memory, reusable skills, and messaging.

Work in your editor

Install the Ollama extension to use models in VS Code Chat.

JetBrains

This example uses IntelliJ; same steps apply to other JetBrains IDEs (e.g., PyCharm).

Install

Install IntelliJ.

Usage with Ollama

To use **Ollama**, you will need a [JetBrains AI Subscription](https://www.jetbrains.com/ai-ides/buy/?section=personal&billing=yearly).

In Intellij, click the chat icon located in the right sidebar

Select the current model in the sidebar, then click Set up Local Models

Under Third Party AI Providers, choose Ollama
Confirm the Host URL is http://localhost:11434, then click Ok
Once connected, select a model under Local models by Ollama

marimo

Install marimo. You can use pip or uv for this. You can also use uv to create a sandboxed environment for marimo by running:

uvx marimo edit --sandbox notebook.py

Usage with Ollama

In marimo, go to the user settings and go to the AI tab. From here you can find and configure Ollama as an AI provider. For local use you would typically point the base url to http://localhost:11434/v1.

Once the AI provider is set up, you can turn on/off specific AI models you'd like to access.

You can also add a model to the list of available models by scrolling to the bottom and using the UI there.

Once configured, you can now use Ollama for AI chats in marimo.

Alternatively, you can now use Ollama for inline code completion in marimo. This can be configured in the "AI Features" tab.

Connecting to ollama.com

n8n

Install n8n.

Using Ollama Locally

In the top right corner, click the dropdown and select Create Credential

Under Add new credential select Ollama

3. Confirm Base URL is set to `http://localhost:11434` if running locally or `http://host.docker.internal:11434` if running through docker and click **Save** In environments that don't use Docker Desktop (ie, Linux server installations), `host.docker.internal` is not automatically added.

Run n8n in docker with --add-host=host.docker.internal:host-gateway

or add the following to a docker compose file:

extra_hosts:
  - "host.docker.internal:host-gateway"

You should see a Connection tested successfully message.

When creating a new workflow, select Add a first step and select an Ollama node

5. Select your model of choice (e.g. `qwen3-coder`)

Connecting to ollama.com

Create an API key on ollama.com.
In n8n, click Create Credential and select Ollama
Set the API URL to https://ollama.com
Enter your API Key and click Save

NemoClaw

NemoClaw is NVIDIA's open source security stack for OpenClaw. It wraps OpenClaw with the NVIDIA OpenShell runtime to provide kernel-level sandboxing, network policy controls, and audit trails for AI agents.

Quick start

Pull a model (see all supported models here):

ollama pull nemotron-3-nano:30b

Run the installer:

curl -fsSL https://www.nvidia.com/nemoclaw.sh | \
  NEMOCLAW_NON_INTERACTIVE=1 \
  NEMOCLAW_PROVIDER=ollama \
  NEMOCLAW_MODEL=nemotron-3-nano:30b \
  bash

Connect to your sandbox:

nemoclaw my-assistant connect

Open the TUI:

openclaw tui

Ollama support in NemoClaw is still experimental.

Platform support

Platform	Runtime	Status
Linux (Ubuntu 22.04+)	Docker	Primary
macOS (Apple Silicon)	Colima or Docker Desktop	Supported
Windows	WSL2 with Docker Desktop	Supported

CMD and PowerShell are not supported on Windows — WSL2 is required.

Ollama must be installed and running before the installer runs. When running inside WSL2 or a container, ensure Ollama is reachable from the sandbox (e.g. OLLAMA_HOST=0.0.0.0).

System requirements

CPU: 4 vCPU minimum
RAM: 8 GB minimum (16 GB recommended)
Disk: 20 GB free (40 GB recommended for local models)
Node.js 20+ and npm 10+
Container runtime (Docker preferred)

Oh My Pi

Oh My Pi (OMP) is a terminal coding agent with IDE-style tools built in. It combines chat, project context, structured code edits, language server support, debugging tools, browser access, plugins, and subagents in one terminal workflow.

Ollama can configure OMP to use Ollama as its model provider and launch an interactive session.

Oh My Pi with Ollama

Quick setup

ollama launch omp

This configures Ollama as a provider, sets up web search tools, and starts OMP.

Run directly with a model

ollama launch omp --model <model>

Plugins

OMP supports plugins for extra tools and capabilities. When launching OMP through Ollama, the Ollama web search plugin is managed automatically.

Manual setup

Install OMP from omp.sh, then run:

ollama launch omp --config

Onyx

Onyx is a self-hostable Chat UI that integrates with all Ollama models. Features include:

Creating custom Agents
Web search
Deep Research
RAG over uploaded documents and connected apps
Connectors to applications like Google Drive, Email, Slack, etc.
MCP and OpenAPI Actions support
Image generation
User/Groups management, RBAC, SSO, etc.

Onyx can be deployed for single users or large organizations.

Install Onyx

Deploy Onyx with the quickstart guide.

Resourcing/scaling docs [here](https://docs.onyx.app/deployment/getting_started/resourcing).

Usage with Ollama

2. In the set-up process select `Ollama` as the LLM provider.

3. Provide your **Ollama API URL** and select your models. If you're running Onyx in Docker, to access your computer's local network use `http://host.docker.internal` instead of `http://127.0.0.1`.

You can also connect Onyx Cloud to Ollama's cloud from the setup flow.

Send your first query

OpenClaw

OpenClaw is a personal AI assistant that runs on your own devices. It bridges messaging services (WhatsApp, Telegram, Slack, Discord, iMessage, and more) to AI coding agents through a centralized gateway.

Quick start

ollama launch openclaw

Ollama handles everything automatically:

Install — If OpenClaw isn't installed, Ollama prompts to install it via npm
Security — On the first launch, a security notice explains the risks of tool access
Model — Pick a model from the selector (see supported local and cloud models here)
Onboarding — Ollama configures the provider, installs the gateway daemon, sets your model as the primary, and enables OpenClaw's bundled Ollama web search
Gateway — Starts in the background and opens the OpenClaw TUI

OpenClaw requires a larger context window. It is recommended to use a context window of at least 64k tokens if using local models. See Context length for more information.

Previously known as Clawdbot. ollama launch clawdbot still works as an alias.

Web search and fetch

OpenClaw ships with a bundled Ollama web_search provider that lets local or cloud-backed Ollama setups search the web through the configured Ollama host.

ollama launch openclaw

Ollama web search is enabled automatically when launching OpenClaw through Ollama. To configure it manually:

openclaw configure --section web

Ollama web search for local models requires ollama signin.

Configure without launching

To change the model without starting the gateway and TUI:

ollama launch openclaw --config

To use a specific model directly:

ollama launch openclaw --model kimi-k2.5:cloud

If the gateway is already running, it restarts automatically to pick up the new model.

Non-interactive (headless) mode

Run OpenClaw without interaction for use in Docker, CI/CD, or scripts:

ollama launch openclaw --model kimi-k2.5:cloud --yes

The --yes flag auto-pulls the model, skips selectors, and requires --model to be specified.

Connect messaging apps

openclaw configure --section channels

Link WhatsApp, Telegram, Slack, Discord, or iMessage to chat with your local models from anywhere.

Stopping the gateway

openclaw gateway stop

OpenCode

OpenCode is an open-source coding agent that runs in your terminal, reads your project, edits files, and runs commands.

Ollama configures OpenCode to use local and cloud models.

Get started

Launch OpenCode with Ollama:

ollama launch opencode

Capabilities

Chat

Ask questions about a repository or task

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="terminal" /></div>
  <div>
    <div className="capability-list-heading">Command line</div>
    <div className="capability-list-copy">Run commands from your working directory</div>
  </div>
</div>

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="code" /></div>
  <div>
    <div className="capability-list-heading">File edits</div>
    <div className="capability-list-copy">Read and edit files in your project</div>
  </div>
</div>

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="users" /></div>
  <div>
    <div className="capability-list-heading">Subagents</div>
    <div className="capability-list-copy">Split work across tasks</div>
  </div>
</div>

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="file-text" /></div>
  <div>
    <div className="capability-list-heading">Web fetch</div>
    <div className="capability-list-copy">Fetch and summarize web pages</div>
  </div>
</div>

<div className="capability-list-item">
  <div className="capability-list-icon"><Icon icon="image" /></div>
  <div>
    <div className="capability-list-heading">Vision</div>
    <div className="capability-list-copy">Send images and screenshots</div>
  </div>
</div>

Models

Choose a model with enough context for your repository.

Use larger models without downloading them. Choose a model and set a 64k+ context window.

OpenCode requires a context length of 64k or higher. See Context length for more information.

Manual setup

1. Install OpenCode

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

npm install -g opencode-ai

2. Configure Ollama as a provider

Add an Ollama provider to opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama",
      "options": {
        "baseURL": "http://localhost:11434/v1"
      },
      "models": {
        "qwen3.5": {
          "name": "qwen3.5"
        }
      }
    }
  }
}

3. Run OpenCode

opencode

To configure OpenCode with Ollama without starting an interactive session:

ollama launch opencode --config

Configuration precedence

ollama launch opencode starts OpenCode with an inline config for the selected Ollama model. It does not overwrite ~/.config/opencode/opencode.json; existing OpenCode settings still apply.

Models defined only in opencode.json do not appear in the ollama launch model picker.

See OpenCode's config precedence.

Pi

Pi is a minimal and extensible coding agent.

Quick setup

ollama launch pi

This installs Pi if needed, configures Ollama as a provider including web tools, and drops you into an interactive session.

To configure without launching:

ollama launch pi --config

Run directly with a model

ollama launch pi --model qwen3.5:cloud

Cloud models are also available at ollama.com.

Extensions

Pi ships with four core tools: read, write, edit, and bash. All other capabilities are added through its extension system.

On-demand capability packages invoked via /skill:name commands.

Install from npm or git:

pi install npm:@foo/some-tools
pi install git:github.com/user/repo@v1

See all packages at pi.dev

Web search

Pi can use web search and fetch tools via the @ollama/pi-web-search package.

When launching Pi through Ollama, package install/update is managed automatically. To install manually:

pi install npm:@ollama/pi-web-search

Autoresearch with `pi-autoresearch`

pi-autoresearch brings autonomous experiment loops to Pi. Inspired by Karpathy's autoresearch, it turns any measurable metric into an optimization target: test speed, bundle size, build time, model training loss, Lighthouse scores.

pi install https://github.com/davebcn87/pi-autoresearch

Tell Pi what to optimize. It runs experiments, benchmarks each one, keeps improvements, reverts regressions, and repeats — all autonomously. A built-in dashboard tracks every run with confidence scoring to distinguish real gains from benchmark noise.

/autoresearch optimize unit test runtime

Each kept experiment is automatically committed. Each failed one is reverted. When you're done, Pi can group improvements into independent branches for clean review and merge.

Manual setup

Install

Install Pi:

npm install -g @earendil-works/pi-coding-agent

Add a configuration block to ~/.pi/agent/models.json:

{
  "providers": {
    "ollama": {
      "baseUrl": "http://localhost:11434/v1",
      "api": "openai-completions",
      "apiKey": "ollama",
      "models": [
        {
          "id": "qwen3-coder"
        }
      ]
    }
  }
}

Update ~/.pi/agent/settings.json to set the default provider:

{
  "defaultProvider": "ollama",
  "defaultModel": "qwen3-coder"
}

Pool

Pool is Poolside's software agent for the terminal, built for enterprise development workflows.

Install

Install Pool:

Usage with Ollama

Quick setup

ollama launch pool

Run directly with a model

ollama launch pool --model kimi-k2.6:cloud

Pass arguments through to Pool

Arguments after -- are passed directly to Pool:

ollama launch pool -- --help

Manual setup

Pool connects to Ollama using the OpenAI-compatible API via environment variables.

Set the environment variables:

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

Run Pool with an Ollama model:

pool -m kimi-k2.6:cloud

Or run with environment variables inline:

POOLSIDE_STANDALONE_BASE_URL=http://localhost:11434/v1 POOLSIDE_API_KEY=ollama pool -m kimi-k2.6:cloud

Roo Code

Install Roo Code from the VS Code Marketplace.

Usage with Ollama

Open Roo Code in VS Code and click the gear icon on the top right corner of the Roo Code window to open Provider Settings
Set API Provider to Ollama
(Optional) Update Base URL if your Ollama instance is running remotely. The default is http://localhost:11434
Enter a valid Model ID (for example qwen3 or qwen3-coder:480b-cloud. See all supported models here)
Adjust the Context Window to at least 32K tokens for coding tasks

Coding tools require a larger context window. It is recommended to use a context window of at least 32K tokens. See Context length for more information.

Connecting to ollama.com

Create an API key from ollama.com
Enable Use custom base URL and set it to https://ollama.com
Enter your Ollama API Key
Select a model from the list

VS Code

Use Ollama models in VS Code Chat with the Ollama extension.

Requirements

Visual Studio Code 1.127 or newer
Ollama installed and running
At least one local or cloud model available in Ollama

Earlier VS Code versions do not reliably cancel requests from language model providers.

Ollama 0.17.6 or newer is recommended for cloud model sign-in and richer model metadata. Older versions may still work with local models.

Install the extension

Install the Ollama extension from the VS Code Marketplace.
Open Chat in VS Code.
Open the model picker at the bottom of the chat input.
Choose a model from the Ollama section.

The extension discovers models from http://127.0.0.1:11434 by default.

Add a model

Pull a local model:

ollama pull qwen3.6

To use a cloud model, pull it and sign in:

ollama pull kimi-k2.6:cloud
ollama signin

Local models do not require sign-in.

Context length

VS Code may show a model's maximum supported context length even when Ollama allocates a smaller context at runtime.

For local models, open Ollama Settings, set the context length to at least 64k, reload the VS Code window, and resend your prompt. See Context length for more information.

Troubleshooting

If Ollama models do not appear in the model picker:

Make sure Ollama is running.
Run ollama list and confirm that models are available.
Run Ollama: Refresh Models from the Command Palette.
Run Ollama: Diagnose Models and check the Ollama output channel.

If a cloud model asks you to sign in, run ollama signin.

Xcode

Install XCode

Usage with Ollama

Ensure Apple Intelligence is setup and the latest XCode version is v26.0

Click XCode in top left corner > Settings

Select Locally Hosted, enter port 11434 and click Add

Select the star icon on the top left corner and click the dropdown

4. Click **My Account** and select your desired model

Connecting to ollama.com directly

Create an API key from ollama.com
Select Internet Hosted and enter URL as https://ollama.com
Enter your Ollama API Key and click Add

Zed

Install Zed.

Usage with Ollama

In Zed, click the star icon in the bottom-right corner, then select Configure.

Under LLM Providers, choose Ollama
Confirm the Host URL is http://localhost:11434, then click Connect
Once connected, select a model under Ollama

Connecting to ollama.com

Create an API key on ollama.com
In Zed, open the star icon → Configure
Under LLM Providers, select Ollama
Set the API URL to https://ollama.com

Integrations

ChatGPT Desktop

Prerequisites

Connect ChatGPT

Choose models

Disconnect ChatGPT

Codex behavior and limits

Related integrations

Claude Code

Get started

Capabilities

Models

More features

Run without interaction

Web search

Scheduled tasks with /loop

Telegram

Connect directly to Ollama's cloud

Manual setup

Claude Desktop

Set up Claude

Switch models

Supported features

Disconnect Claude

Cline CLI

Install

Usage with Ollama

Quick setup

Run directly with a model

Pass a prompt to Cline

Manual setup

Cline

Usage with Ollama

Connecting to ollama.com

Models

Codex CLI

Usage with Ollama

Quick setup

Manual setup

Profile-based setup

Web search through local Ollama

Copilot CLI

Install

Usage with Ollama

Quick setup

Run directly with a model

Non-interactive (headless) mode

Manual setup

DeepSeek Harness

Setup

Web search

Configuration

Manual install

Droid

Usage with Ollama

Quick setup

Manual setup

Cloud Models

Connecting to ollama.com

Goose

Usage with Ollama

Connecting to ollama.com

Goose CLI

Usage with Ollama

Connecting to ollama.com

Hermes Desktop

Quick start

Run directly with a model

Install Hermes Desktop directly

Hermes Agent

Quick start

Connect messaging apps

Reconfigure

Manual setup

Connect to Ollama

Connect messaging

Launch

Overview

Launch a coding agent

Connect a desktop app

Scheduled tasks with `/loop`

Autoresearch with `pi-autoresearch`