bambu-studio-ai
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
Manage multi-provider model switching and fallback chains in OpenClaw. "OpenClaw Switch" helps users set up automatic model failover (e.g. 429 rate-limit → fallback), switch primary models, view current fallback chains, and configure heartbeat/subagent routing. Works with any provider (Gemini, OpenAI, Anthropic, NVIDIA, Ollama, etc.).
请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。
SkillHub CLI
skillhub install 2233admin/openclaw-switch打开来源仓库,查看说明和兼容环境后,按来源提供的命令或步骤安装。
将来源链接提供给你的 Agent,让它先读取说明、核对依赖,并向你说明将执行的安装步骤。
The missing model manager for OpenClaw. Switch models, visualize fallback chains, and manage multi-provider setups.
# Show current model, fallback chain, heartbeat & subagent config
bash {baseDir}/scripts/openclaw-switch.sh status
# List all available models across all providers
bash {baseDir}/scripts/openclaw-switch.sh list
# Switch primary model (by number from list)
bash {baseDir}/scripts/openclaw-switch.sh switch 2
# Show fallback chain only
bash {baseDir}/scripts/openclaw-switch.sh fallback
OpenClaw natively supports model.fallbacks — when the primary model returns an error (429, 500, etc.), the next model in the chain is tried automatically. OpenClaw Switch helps users configure, visualize, and toggle this chain.
Register multiple providers in openclaw.json, each with its own API key:
{
"models": {
"providers": {
"provider-a": { "apiKey": "...", "models": [{ "id": "model-1" }] },
"provider-b": { "apiKey": "...", "models": [{ "id": "model-2" }] }
}
},
"agents": {
"defaults": {
"model": {
"primary": "provider-a/model-1",
"fallbacks": ["provider-b/model-2"]
}
}
}
}
The bundled script:
bash + python3 stdlib — zero external dependencies
这些信息来自收录时的来源分析,可能滞后;使用前请核对最新来源文件。
"The missing remote control for your AI Agents."
OpenClaw Switch 是一个为 OpenClaw 量身定制的模型管理与一键切换工具。它解决了手动修改 openclaw.json 容易导致格式错误并导致 Gateway 崩溃的痛点。
switch 2)在不同供应商(Google, OpenAI, Kimi, etc.)之间秒切。进入你的 OpenClaw 技能目录并克隆本仓库:
cd ~/.openclaw/skills
git clone https://github.com/sarahmirrand001-oss/openclaw-switch.git
为了能在任何地方直接使用 openclaw-switch 命令,你需要确保 OpenClaw 的 bin 目录在你的系统路径中。
执行以下命令(适用于 macOS/Linux 的 ZSH 用户):
echo 'export PATH="$HOME/.openclaw/bin:$PATH"' >> ~/.zshrc
source ~/.zshrc
进入技能文件夹后运行脚本:
查看当前主模型、备份链以及心跳任务的配置。
bash scripts/openclaw-switch.sh status
获取所有已配置模型的数字编号。
bash scripts/openclaw-switch.sh list
通过 list 命令得到的数字编号,快速切换主模型。
# 比如切换到列表中的第 2 个模型
bash scripts/openclaw-switch.sh switch 2
查看当主模型失效时,OpenClaw 会按什么顺序尝试其他模型。
bash scripts/openclaw-switch.sh fallback
建议在 openclaw.json 中配置多个供应商以实现自动容灾:
"model": {
"primary": "google/gemini-1.5-pro",
"fallbacks": ["google-backup/ge...
# OpenClaw Switch
The missing model manager for OpenClaw. Switch models, visualize fallback chains, and manage multi-provider setups.
## Quick start
```bash
# Show current model, fallback chain, heartbeat & subagent config
bash {baseDir}/scripts/openclaw-switch.sh status
# List all available models across all providers
bash {baseDir}/scripts/openclaw-switch.sh list
# Switch primary model (by number from list)
bash {baseDir}/scripts/openclaw-switch.sh switch 2
# Show fallback chain only
bash {baseDir}/scripts/openclaw-switch.sh fallback
```
## How it works
OpenClaw natively supports `model.fallbacks` — when the primary model returns an error (429, 500, etc.), the next model in the chain is tried automatically. OpenClaw Switch helps users **configure, visualize, and toggle** this chain.
### Typical setup
Register multiple providers in `openclaw.json`, each with its own API key:
```json
{
"models": {
"providers": {
"provider-a": { "apiKey": "...", "models": [{ "id": "model-1" }] },
"provider-b": { "apiKey": "...", "models": [{ "id": "model-2" }] }
}
},
"agents": {
"defaults": {
"model": {
"primary": "provider-a/model-1",
"fallbacks": ["provider-b/model-2"]
}
}
}
}
```
### Use cases
- **Same provider, two API keys** (e.g. paid + free Gemini) — register as separate providers
- **Cross-provider failover** (e.g. Gemini → OpenAI → local Ollama)
- **Cost optimization** — route heartbeat/subagents to cheaper or free models
## Security
The bundled script:
- **Never transmits** API keys or config data over the network
- **Never logs** full API keys (masks all but first 8 chars)
- Uses only `bash` + `python3` stdlib — **zero external dependencies**
- Source is < 150 lines — **fully auditable in 2 minutes**# 🔀 OpenClaw Switch
> "The missing remote control for your AI Agents."
**OpenClaw Switch** 是一个为 OpenClaw 量身定制的模型管理与一键切换工具。它解决了手动修改 `openclaw.json` 容易导致格式错误并导致 Gateway 崩溃的痛点。
---
## ✨ 核心功能 (Features)
- **🚫 拒绝崩溃**: 采用 Python 原生解析 JSON,确保配置文件修改永远合法,彻底告别由于手动修改带来的格式错误。
- **📊 可视化 Failover**: 直观展示你的模型备份链(Fallback chain)。当主模型 (429/500) 报错时,一眼看出下一个接管的模型是谁。
- **🚀 丝滑切换**: 告别复杂的模型 ID,直接通过数字编号(如 `switch 2`)在不同供应商(Google, OpenAI, Kimi, etc.)之间秒切。
- **💓 路由透明**: 清晰显示 Heartbeat(心跳)和 Subagents(子智能体)当前路由的模型路径。
- **🛡️ 极致安全**: 纯本地运行,不联网,不上传 API Key,仅显示 Key 的前 8 位用于辨认。
---
## 🛠 安装指南 (Installation)
### 1. 克隆插件
进入你的 OpenClaw 技能目录并克隆本仓库:
```bash
cd ~/.openclaw/skills
git clone https://github.com/sarahmirrand001-oss/openclaw-switch.git
```
### 2. 激活命令 (重要)
为了能在任何地方直接使用 `openclaw-switch` 命令,你需要确保 OpenClaw 的 bin 目录在你的系统路径中。
**执行以下命令(适用于 macOS/Linux 的 ZSH 用户):**
```bash
echo 'export PATH="$HOME/.openclaw/bin:$PATH"' >> ~/.zshrc
source ~/.zshrc
```
---
## 📖 使用手册 (Usage)
进入技能文件夹后运行脚本:
### 1. 查看当前状态
查看当前主模型、备份链以及心跳任务的配置。
```bash
bash scripts/openclaw-switch.sh status
```
### 2. 列出所有模型
获取所有已配置模型的数字编号。
```bash
bash scripts/openclaw-switch.sh list
```
### 3. 一键切换主模型
通过 `list` 命令得到的数字编号,快速切换主模型。
```bash
# 比如切换到列表中的第 2 个模型
bash scripts/openclaw-switch.sh switch 2
```
### 4. 查看备份逻辑
查看当主模型失效时,OpenClaw 会按什么顺序尝试其他模型。
```bash
bash scripts/openclaw-switch.sh fallback
```
---
## ⚙️ 进阶配置建议 (Best Practice)
建议在 `openclaw.json` 中配置多个供应商以实现自动容灾:
```json
"model": {
"primary": "google/gemini-1.5-pro",
"fallbacks": ["google-backup/ge...Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discove...
Local speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). 30x faster than Whisper, 25 languages, auto-detection, OpenAI-compatible API. Use when transcribing audio files, converting speech to text, o...
飞书消息自动处理与进度反馈技能。安装后后台运行,监听飞书任务消息并自动创建独立进程处理。 在处理前后发送实时进度反馈(任务确认、进度百分比、完成通知)。 支持任务类型识别、智能解析、错误重试、并发控制、状态持久化...