OpenClaw

nadirclaw

Install, configure, and run NadirClaw LLM router to cut AI API costs by 40-70%. Use when the user wants to reduce LLM spending, route prompts to cheaper models, set up cost-saving proxy, or optimize API usage across providers (OpenAI, Anthropic, Google, Ollama). Also use when asked about model routing, LLM cost optimization, or setting up NadirClaw with OpenClaw.

doramirdor0 来源安装数☆ 0 仓库 Starsv1.0.0

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

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 doramirdor/nadirclaw

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。

查看来源 ↗使用指南

技能说明

NadirClaw Skill

NadirClaw is an open-source LLM router that classifies prompts in ~10ms and routes simple ones to cheap/local models while keeping complex work on premium models.

Install

pip install nadirclaw

Setup

Run the interactive wizard:

nadirclaw setup

Or auto-configure for OpenClaw:

nadirclaw openclaw onboard

This writes NadirClaw as a provider in OpenClaw config with model nadirclaw/auto. No restart needed.

Start

nadirclaw serve --verbose

Runs on http://localhost:8856. Any OpenAI-compatible tool can use it by pointing to this URL.

Point tools at NadirClaw

# OpenClaw (auto)
nadirclaw openclaw onboard

# Claude Code
ANTHROPIC_BASE_URL=http://localhost:8856/v1 claude

# Any OpenAI-compatible tool
OPENAI_BASE_URL=http://localhost:8856/v1 <tool>

Routing profiles

Pass x-routing-profile header or use these models:

nadirclaw/auto - smart routing (default)
nadirclaw/eco - maximize savings
nadirclaw/premium - always use best model
nadirclaw/free - Ollama/local only
nadirclaw/reasoning - chain-of-thought optimized

Monitor savings

nadirclaw savings      # cost savings report
nadirclaw report       # detailed routing analytics
nadirclaw dashboard    # live terminal dashboard

Key features

~10ms classification overhead
Session persistence (no model bouncing mid-conversation)
Rate limit fallback (auto-retry on 429)
Agentic task detection (forces premium for tool use)
Context-window filtering (auto-swaps for long conversations)
Supports: OpenAI, Anthropic, Google Gemini, Ollama, any LiteLLM provider

Troubleshooting

If nadirclaw serve fails, check API keys: nadirclaw setup
For Ollama: ensure ollama serve is running first
Logs: nadirclaw report --last 20 to see recent routing decisions
Raw debug: nadirclaw serve --verbose --log-raw

来源信息

Source: github
Repository: openclaw/skills
Path: skills/doramirdor/nadirclaw
Version: 1.0.0
Commit: 165d1528e4711898d3596a4c4c1d0fc7004d9fb2
分类来源: rules
状态: active
可见性: public

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。

来源内容

SKILL.md

# NadirClaw Skill

NadirClaw is an open-source LLM router that classifies prompts in ~10ms and routes simple ones to cheap/local models while keeping complex work on premium models.

## Install

```bash
pip install nadirclaw
```

## Setup

Run the interactive wizard:
```bash
nadirclaw setup
```

Or auto-configure for OpenClaw:
```bash
nadirclaw openclaw onboard
```

This writes NadirClaw as a provider in OpenClaw config with model `nadirclaw/auto`. No restart needed.

## Start

```bash
nadirclaw serve --verbose
```

Runs on `http://localhost:8856`. Any OpenAI-compatible tool can use it by pointing to this URL.

## Point tools at NadirClaw

```bash
# OpenClaw (auto)
nadirclaw openclaw onboard

# Claude Code
ANTHROPIC_BASE_URL=http://localhost:8856/v1 claude

# Any OpenAI-compatible tool
OPENAI_BASE_URL=http://localhost:8856/v1 <tool>
```

## Routing profiles

Pass `x-routing-profile` header or use these models:
- `nadirclaw/auto` - smart routing (default)
- `nadirclaw/eco` - maximize savings
- `nadirclaw/premium` - always use best model
- `nadirclaw/free` - Ollama/local only
- `nadirclaw/reasoning` - chain-of-thought optimized

## Monitor savings

```bash
nadirclaw savings      # cost savings report
nadirclaw report       # detailed routing analytics
nadirclaw dashboard    # live terminal dashboard
```

## Key features

- ~10ms classification overhead
- Session persistence (no model bouncing mid-conversation)
- Rate limit fallback (auto-retry on 429)
- Agentic task detection (forces premium for tool use)
- Context-window filtering (auto-swaps for long conversations)
- Supports: OpenAI, Anthropic, Google Gemini, Ollama, any LiteLLM provider

## Troubleshooting

- If `nadirclaw serve` fails, check API keys: `nadirclaw setup`
- For Ollama: ensure `ollama serve` is running first
- Logs: `nadirclaw report --last 20` to see recent routing decisions
- Raw debug: `nadirclaw serve --verbose --log-raw`

搜索