mirror of
https://github.com/ollama/ollama.git
synced 2026-04-18 20:54:12 +02:00
docs: update instructions for ollama config command
These tools can be automatically configured using the new ollama config command
This commit is contained in:
63
docs/integrations/opencode.mdx
Normal file
63
docs/integrations/opencode.mdx
Normal file
@@ -0,0 +1,63 @@
|
||||
---
|
||||
title: OpenCode
|
||||
---
|
||||
|
||||
OpenCode is an agentic coding tool for the terminal.
|
||||
|
||||
## Install
|
||||
|
||||
Install [OpenCode](https://opencode.ai):
|
||||
|
||||
```shell
|
||||
curl -fsSL https://opencode.ai/install | bash
|
||||
```
|
||||
|
||||
## Usage with Ollama
|
||||
|
||||
Configure OpenCode to use Ollama:
|
||||
|
||||
```shell
|
||||
ollama config opencode
|
||||
```
|
||||
|
||||
This will prompt you to select models and automatically configure OpenCode to use Ollama.
|
||||
|
||||
<Accordion title="Manual Configuration">
|
||||
|
||||
Add the Ollama provider to `~/.config/opencode/opencode.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"$schema": "https://opencode.ai/config.json",
|
||||
"provider": {
|
||||
"ollama": {
|
||||
"npm": "@ai-sdk/openai-compatible",
|
||||
"name": "Ollama (local)",
|
||||
"options": {
|
||||
"baseURL": "http://localhost:11434/v1"
|
||||
},
|
||||
"models": {
|
||||
"qwen3-coder": {
|
||||
"name": "qwen3-coder [Ollama]"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
</Accordion>
|
||||
|
||||
<Note>OpenCode requires a larger context window. It is recommended to use a context window of at least 32K tokens. See [Context length](/context-length) for more information.</Note>
|
||||
|
||||
## Recommended Models
|
||||
|
||||
### Cloud models
|
||||
- `qwen3-coder:480b` - Large coding model
|
||||
- `glm-4.7:cloud` - High-performance cloud model
|
||||
- `minimax-m2.1:cloud` - Fast cloud model
|
||||
|
||||
### Local models
|
||||
- `qwen3-coder` - Excellent for coding tasks
|
||||
- `gpt-oss:20b` - Strong general-purpose model
|
||||
- `gpt-oss:120b` - Larger general-purpose model for more complex tasks
|
||||
Reference in New Issue
Block a user