mirror of
https://github.com/ollama/ollama.git
synced 2026-02-05 05:03:21 -05:00
51 lines
1.2 KiB
Plaintext
51 lines
1.2 KiB
Plaintext
---
|
|
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
|
|
|
|
```bash
|
|
ollama launch openclaw
|
|
```
|
|
|
|
<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.
|
|
|
|
|
|
To configure without launching:
|
|
|
|
```shell
|
|
ollama launch openclaw --config
|
|
```
|
|
|
|
## 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).
|