# Omnirush Models

Manage OmniRush.ai inference model aliases, omnirush model overlays, discounts...

- Repository: https://github.com/omnirush-ai/omnirush-gui (4595 stars)
- Category: Git and review
- License: see repository
- Last updated: 2026-10-30
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add omnirush-ai/omnirush-gui --skill omnirush-models -g -a claude-code -y`
Codex: `npx skills add omnirush-ai/omnirush-gui --skill omnirush-models -g -a codex -y`
Cursor: `npx skills add omnirush-ai/omnirush-gui --skill omnirush-models -g -a cursor -y`
Gemini CLI: `npx skills add omnirush-ai/omnirush-gui --skill omnirush-models -g -a gemini-cli -y`

## Description

Manage OmniRush.ai inference model aliases, omnirush model overlays, discounts, validation, and automated base model refreshes from models.dev. Use when adding, removing, discounting, auditing, or updating OmniRush.ai models, including requests like "update the models" that should trigger the GitHub update-models workflow and report when its PR merges.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# OmniRush.ai Models

Use this skill for OmniRush.ai inference model changes. The source of truth for
available upstream models is:

- `ee/apps/inference/src/models/base.json`
- provider key: `openrouter`
- model map: `openrouter.models`

The editable OmniRush.ai model list is:

- `ee/apps/inference/src/models/omnirush-models.json`

Managed file:

- `packages/types/src/den/inference.ts`

`ee/apps/inference/scripts/build-models.mjs` reads `omnirush-models.json` and
generates the OmniRush.ai provider overlay in memory. It selects the API URL from
`OMNIRUSH_DEV_MODE`: dev uses `http://127.0.0.1:8791/api/v1`; the non-dev value
hard-coded there points at the retired hosted `inference.omnirushlabs.com`
domain, which omnirush.ai no longer owns. Do not treat that origin as a live
endpoint or copy it into new configuration.

Do not inspect the full `base.json` in chat. Use the scripts so the large source
model body stays out of context.

## Scripts

Extract/search source models into a temp file:

```bash
node .opencode/skills/omnirush-models/scripts/extract-source-models.mjs
node .opencode/skills/omnirush-models/scripts/extract-source-models.mjs --query "zai 5.1"
```

Manage OmniRush.ai models:

```bash
node .opencode/skills/omnirush-models/scripts/omnirush-models.mjs search "zai 5.1"
node .opencode/skills/omnirush-models/scripts/omnirush-models.mjs add "z-ai/glm-5.1"
node .opencode/skills/omnirush-models/scripts/omnirush-models.mjs remove "z-ai/glm-5.1"
node .opencode/skills/omnirush-models/scripts/omnirush-models.mjs discount 0.1 "z-ai/glm-5.1"
node .opencode/skills/omnirush-models/scripts/omnirush-models.mjs sync
node .opencode/skills/omnirush-models/scripts/omnirush-models.mjs validate
```

Trigger the remote base model refresh workflow:

```bash
node .opencode/skills/omnirush-models/scripts/trigger-update-workflow.mjs
node .opencode/skills/omnirush-models/scripts/trigger-update-workflow.mjs --base dev --ref dev
```

## Update Models Workflow

The rest: https://github.com/omnirush-ai/omnirush-gui/blob/HEAD/.opencode/skills/omnirush-models/SKILL.md