Sync ollama docs from 8f45236d on 2026-03-12

2026-03-12 04:00:04 +00:00
parent 6bfb23ec9f
commit 1c2aec910d
15 changed files with 324 additions and 190 deletions
@@ -4,7 +4,7 @@ title: Claude Code

 Claude Code is Anthropic's agentic coding tool that can read, modify, and execute code in your working directory. 

-Open models can be used with Claude Code through Ollama's Anthropic-compatible API, enabling you to use models such as `glm-4.7`, `qwen3-coder`, `gpt-oss`. 
+Open models can be used with Claude Code through Ollama's Anthropic-compatible API, enabling you to use models such as `qwen3.5`, `glm-5:cloud`, `kimi-k2.5:cloud`.

 ![Claude Code with Ollama](https://files.ollama.com/claude-code.png)

@@ -32,13 +32,57 @@ irm https://claude.ai/install.ps1 | iex
 ollama launch claude
 ```

-To configure without launching:
-
+### Run directly with a model
 ```shell
-ollama launch claude --config
+ollama launch claude --model kimi-k2.5:cloud
 ```

-### Manual setup
+## Recommended Models
+
+- `kimi-k2.5:cloud`
+- `glm-5:cloud`
+- `minimax-m2.5:cloud`
+- `qwen3.5:cloud`
+- `glm-4.7-flash`
+- `qwen3.5`
+
+Cloud models are also available at [ollama.com/search?c=cloud](https://ollama.com/search?c=cloud).
+
+## Scheduled Tasks with `/loop`
+
+The `/loop` command runs a prompt or slash command on a recurring schedule inside Claude Code. This is useful for automating repetitive tasks like checking PRs, running research, or setting reminders.
+
+```
+/loop <interval> <prompt or /command>
+```
+
+### Examples
+
+**Check in on your PRs**
+
+```
+/loop 30m Check my open PRs and summarize their status
+```
+
+**Automate research tasks**
+
+```
+/loop 1h Research the latest AI news and summarize key developments
+```
+
+**Automate bug reporting and triaging**
+
+```
+/loop 15m Check for new GitHub issues and triage by priority
+```
+
+**Set reminders**
+
+```
+/loop 1h Remind me to review the deploy status
+```
+
+## Manual setup

 Claude Code connects to Ollama using the Anthropic-compatible API.

@@ -53,23 +97,14 @@ export ANTHROPIC_BASE_URL=http://localhost:11434
 2. Run Claude Code with an Ollama model:

 ```shell
-claude --model gpt-oss:20b
+claude --model qwen3.5
 ```

 Or run with environment variables inline:

 ```shell
-ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 ANTHROPIC_API_KEY="" claude --model qwen3-coder 
+ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 ANTHROPIC_API_KEY="" claude --model glm-5:cloud
 ```

 **Note:** Claude Code requires a large context window. We recommend at least 64k tokens. See the [context length documentation](/context-length) for how to adjust context length in Ollama.

-## Recommended Models
-
- `qwen3-coder` 
- `glm-4.7`
- `gpt-oss:20b`
- `gpt-oss:120b`
-
-Cloud models are also available at [ollama.com/search?c=cloud](https://ollama.com/search?c=cloud).
-
@@ -13,6 +13,7 @@ Coding assistants that can read, modify, and execute code in your projects.
 - [OpenCode](/integrations/opencode)
 - [Droid](/integrations/droid)
 - [Goose](/integrations/goose)
+- [Pi](/integrations/pi)

 ## Assistants

@@ -4,47 +4,65 @@ title: 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.

-## Install
-
-Install [OpenClaw](https://openclaw.ai/) 
-
-```bash
-npm install -g openclaw@latest
-```
-
-Then run the onboarding wizard:
-
-```bash
-openclaw onboard --install-daemon
-```
-
-<Note>OpenClaw requires a larger context window. It is recommended to use a context window of at least 64k tokens. See [Context length](/context-length) for more information.</Note>
-
-## Usage with Ollama
-
-### Quick setup
+## Quick start

 ```bash
 ollama launch openclaw
 ```

+Ollama handles everything automatically:
+
+1. **Install** — If OpenClaw isn't installed, Ollama prompts to install it via npm
+2. **Security** — On the first launch, a security notice explains the risks of tool access
+3. **Model** — Pick a model from the selector (local or cloud)
+4. **Onboarding** — Ollama configures the provider, installs the gateway daemon, and sets your model as the primary
+5. **Gateway** — Starts in the background and opens the OpenClaw TUI
+
+<Note>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](/context-length) for more information.</Note>
+
 <Note>Previously known as Clawdbot. `ollama launch clawdbot` still works as an alias.</Note>

-This configures OpenClaw to use Ollama and starts the gateway.
-If the gateway is already running, no changes need to be made as the gateway will auto-reload the changes. 
+## Configure without launching

+To change the model without starting the gateway and TUI:

-To configure without launching:
-
-```shell
+```bash
 ollama launch openclaw --config
 ```

-## Recommended Models
+To use a specific model directly:

- `qwen3-coder`
- `glm-4.7`
- `gpt-oss:20b`
- `gpt-oss:120b`
+```bash
+ollama launch openclaw --model kimi-k2.5:cloud
+```
+
+If the gateway is already running, it restarts automatically to pick up the new model.
+
+## Recommended models
+
+**Cloud models**:
+
+- `kimi-k2.5:cloud` — Multimodal reasoning with subagents
+- `minimax-m2.5:cloud` — Fast, efficient coding and real-world productivity
+- `glm-5:cloud` — Reasoning and code generation
+
+**Local models:**
+
+- `glm-4.7-flash` — Reasoning and code generation locally (~25 GB VRAM)
+
+More models at [ollama.com/search](https://ollama.com/search?c=cloud).
+
+## Connect messaging apps
+
+```bash
+openclaw configure --section channels
+```
+
+Link WhatsApp, Telegram, Slack, Discord, or iMessage to chat with your local models from anywhere.
+
+## Stopping the gateway
+
+```bash
+openclaw gateway stop
+```

-Cloud models are also available at [ollama.com/search?c=cloud](https://ollama.com/search?c=cloud).
@@ -0,0 +1,57 @@
+---
+title: Pi
+---
+
+Pi is a minimal AI agent toolkit with plugin support.
+
+## Install
+
+Install [Pi](https://github.com/badlogic/pi-mono):
+
+```bash
+npm install -g @mariozechner/pi-coding-agent
+```
+
+## Usage with Ollama
+
+### Quick setup
+
+```bash
+ollama launch pi
+```
+
+To configure without launching:
+
+```shell
+ollama launch pi --config
+```
+
+### Manual setup
+
+Add a configuration block to `~/.pi/agent/models.json`:
+
+```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:
+
+```json
+{
+  "defaultProvider": "ollama",
+  "defaultModel": "qwen3-coder"
+}
+```