Sync ollama docs from 53fed261 on 2026-09-12
This commit is contained in:
The Librarian
@@ -1,13 +1,42 @@
|
||||
---
|
||||
title: Claude Desktop
|
||||
description: Use Ollama models in Claude on macOS.
|
||||
---
|
||||
|
||||
Claude Desktop is no longer supported by `ollama launch`.
|
||||
|
||||
Existing installations can be restored to the usual Claude profile:
|
||||
## Prerequisites
|
||||
|
||||
- [Ollama](https://ollama.com/download/). Windows support coming soon.
|
||||
- To use a local model, [download it](/quickstart#3-start-a-chat) before setup.
|
||||
- To use a cloud model, sign in to Ollama and enable cloud models. Some models require a [paid plan](https://ollama.com/pricing).
|
||||
|
||||
If Claude is not installed, Ollama offers to download it during setup.
|
||||
|
||||
## Set up Claude
|
||||
|
||||
1. Open Ollama and select **Apps**.
|
||||
2. Toggle Claude to On.
|
||||
3. If Claude is not installed, Ollama will download and finish the installation.
|
||||
|
||||
## Switch models
|
||||
|
||||
Open Ollama **Settings**. Under **Apps**, choose a model you want to use, then select **Restart Claude**. You can assign the same Ollama model to more than one option.
|
||||
|
||||
## Supported features
|
||||
|
||||
- **Subagents** - Split larger tasks across agents
|
||||
- **Web search** - Supported by default through [Ollama's web search](/capabilities/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 turn Claude off. Ollama restores Claude's previous configuration. If Claude is open, Ollama asks to restart it so the change takes effect.
|
||||
|
||||
You can also restore Claude from the terminal:
|
||||
|
||||
```shell
|
||||
ollama launch claude-desktop --restore
|
||||
```
|
||||
|
||||
Use [Claude Code](/integrations/claude-code) for Anthropic-compatible coding workflows with Ollama.
|
||||
Quitting Ollama while Claude is connected also restores Claude's usual configuration.
|
||||
|
||||
@@ -76,3 +76,15 @@ Then run:
|
||||
```
|
||||
codex --profile ollama-launch
|
||||
```
|
||||
|
||||
## Web search
|
||||
|
||||
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:
|
||||
|
||||
```shell
|
||||
codex --profile ollama-launch -c 'web_search="disabled"'
|
||||
```
|
||||
|
||||
@@ -0,0 +1,50 @@
|
||||
---
|
||||
title: DeepSeek Harness
|
||||
---
|
||||
|
||||
[DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) is an open-source coding agent.
|
||||
|
||||
<Note>DeepSeek Harness is currently a developer preview. Its upstream configuration may change between releases.</Note>
|
||||
|
||||
## Setup
|
||||
|
||||
```shell
|
||||
ollama launch dsh
|
||||
```
|
||||
|
||||
Ollama installs `@deepseek-ai/dsh` if needed. To choose a model:
|
||||
|
||||
```shell
|
||||
ollama launch dsh --model qwen3.8
|
||||
ollama launch dsh --model deepseek-v4-flash:cloud
|
||||
```
|
||||
|
||||
To configure without starting:
|
||||
|
||||
```shell
|
||||
ollama launch dsh --config
|
||||
```
|
||||
|
||||
## Web search
|
||||
|
||||
Web search is enabled automatically. It requires Ollama cloud access 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 `--`:
|
||||
|
||||
```shell
|
||||
ollama launch dsh -- --port 3081
|
||||
```
|
||||
|
||||
## Manual install
|
||||
|
||||
DeepSeek Harness requires Node.js. To install it manually:
|
||||
|
||||
```shell
|
||||
npm install -g @deepseek-ai/dsh@latest
|
||||
```
|
||||
|
||||
Then run `ollama launch dsh`. On Windows, install Node.js for Windows.
|
||||
@@ -17,13 +17,21 @@ Run `ollama launch` to see the latest integrations you can run from the terminal
|
||||
<Card title="OpenCode" icon="/images/launch-icons/opencode.svg" href="/integrations/opencode">
|
||||
Open-source coding agent that edits, runs, and iterates on code.
|
||||
</Card>
|
||||
|
||||
<Card title="DeepSeek Harness" icon="/images/launch-icons/deepseek-harness.svg" href="/integrations/deepseek-harness">
|
||||
DeepSeek's open-source agent harness with subagents and web search.
|
||||
</Card>
|
||||
</CardGroup>
|
||||
|
||||
## Connect an assistant
|
||||
|
||||
Assistants with memory, skills, and messaging app access.
|
||||
Use open models in assistant apps.
|
||||
|
||||
<CardGroup cols={2}>
|
||||
<Card title="Claude" href="/integrations/claude-desktop">
|
||||
Desktop assistant with local and cloud Ollama models.
|
||||
</Card>
|
||||
|
||||
<Card title="OpenClaw" icon="/images/launch-icons/openclaw.svg" href="/integrations/openclaw">
|
||||
Personal assistant for messaging apps and everyday tasks.
|
||||
</Card>
|
||||
|
||||
Reference in New Issue
Block a user