← 返回
未分类 中文

Api Model list updater

Query available models from your configured providers and add them to OpenClaw config
查询已配置提供商的可用模型并添加到 OpenClaw 配置
da-kaine da-kaine 来源
未分类 clawhub v0.0.1 1 版本 100000 Key: 无需
★ 0
Stars
📥 143
下载
💾 0
安装
1
版本
#latest

概述

Model Catalog Updater

Fetch available models from your configured API providers and add them to your OpenClaw config.

How It Works

When invoked, this skill:

  1. Reads your config → Loads providers from openclaw.json
  2. Presents choices → Shows numbered list of your configured providers
  3. User selects provider → Queries /v1/models from that provider
  4. Shows available models → Lists models with IDs
  5. User picks models → Select which to add (comma-separated or 'all')
  6. Creates backup → Saves openclawworking.json before any edits
  7. Updates config → Adds models to both:
    • models.providers.{provider}.models[] — model definitions
    • agents.defaults.models.{provider/model-id} — alias entries

Usage

Slash command:

  • /model-catalog-updater provider:

Natural language:

  • "show me available models"
  • "add models from openrouter"
  • "what models are on lmstudio"

Configuration

SettingValue
----------------
Config pathC:\Users\zebuM\.openclaw\openclaw.json
Backup fileopenclawworking.json (same directory)
Default context window128000
Default max tokens8192

Reasoning Detection

Models are auto-detected as reasoning models if their ID contains:

  • deepseek-r1
  • qwq
  • o1
  • o3
  • reasoning
  • think

Model Entry Format

Added to models.providers.{provider}.models:

{
  "id": "model-id",
  "name": "Display Name",
  "reasoning": false,
  "input": ["text"],
  "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 },
  "contextWindow": 128000,
  "maxTokens": 8192
}

Alias Entry Format

Added to agents.defaults.models:

"provider/model-id": {}

(Empty object — user can add "alias": "short-name" manually if desired)

Example Session

📊 Model Catalog

Your configured providers:
1. qwen-portal (https://portal.qwen.ai/v1)
2. lmstudio (http://192.168.56.1:1234/v1)
3. xai (https://api.x.ai/v1)
4. openrouter (https://openrouter.ai/api/v1)
5. modal-direct (https://api.us-west-2.modal.direct/v1)
6. cloudflare-ai-gateway
7. minimax

Select provider [1-7]: 3

Fetching models from xai...

Available models:
1. grok-4
2. grok-4-vision
3. grok-2-1212

Select models to add (comma-separated, or 'all'): 1,2

✅ Backup created: openclawworking.json
✅ Added to models.providers.xai.models:
   - grok-4
   - grok-4-vision
✅ Added to agents.defaults.models:
   - xai/grok-4
   - xai/grok-4-vision

Notes

  • Some providers don't expose /v1/models (e.g., Cloudflare AI Gateway)
  • Vision models get "input": ["text", "image"] automatically if ID contains "vision" or "multimodal"
  • Restart OpenClaw after adding models to apply changes

版本历史

共 1 个版本

  • v0.0.1 当前
    2026-05-12 06:22

安全检测

腾讯云安全 (Keen)

队列中

腾讯云安全 (Sanbu)

队列中

🔗 相关推荐

dev-programming

Github

steipete
使用 `gh` CLI 与 GitHub 交互,通过 `gh issue`、`gh pr`、`gh run` 和 `gh api` 管理议题、PR、CI 运行及高级查询。
★ 681 📥 329,972
dev-programming

YouTube

byungkyu
使用托管OAuth集成YouTube Data API,支持搜索视频、管理播放列表、获取频道数据及评论互动,适用于用户需要时使用此技能。
★ 142 📥 41,952
dev-programming

CodeConductor.ai

larsonreever
AI驱动平台,提供快速全栈开发、智能体、工作流自动化及低代码AI集成的可扩展产品创建。
★ 78 📥 182,640