admin/ClaudeCode-Custom-Skills
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: Comprehensive documentation for 25+ providers + Qwen OAuth

Browse Source 
Restructured documentation to highlight both key features:

FEATURE 1: Qwen OAuth Cross-Platform Import (FREE)
- 2,000 requests/day free tier
- Works with ALL Claw platforms
- Browser OAuth via qwen.ai
- Model: Qwen3-Coder

FEATURE 2: 25+ OpenCode-Compatible Providers
- Major AI Labs: Anthropic, OpenAI, Google, xAI, Mistral
- Cloud Platforms: Azure, AWS Bedrock, Google Vertex
- Fast Inference: Groq, Cerebras
- Gateways: OpenRouter (100+ models), Together AI
- Local: Ollama, LM Studio, vLLM

Provider Tiers:
1. FREE: Qwen OAuth
2. Major Labs: Anthropic, OpenAI, Google, xAI, Mistral
3. Cloud: Azure, Bedrock, Vertex
4. Fast: Groq, Cerebras
5. Gateways: OpenRouter, Together AI, Vercel
6. Specialized: Perplexity, Cohere, GitLab, GitHub
7. Local: Ollama, LM Studio, vLLM

Platforms with full support:
- Qwen Code (native OAuth)
- OpenClaw, NanoBot, PicoClaw, ZeroClaw (import OAuth)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Claude Code
2026-02-22 04:19:29 -05:00
Unverified
parent 46ed77201c
commit 4299e9dce4
3 changed files with 468 additions and 446 deletions
Download Patch File Download Diff File Expand all files Collapse all files

337
skills/claw-setup/README.md
View File

@@ -2,9 +2,9 @@
# 🦞 Claw Setup
### Cross-Platform AI Agent Deployment with FREE Qwen OAuth
### Cross-Platform AI Agent Deployment with 25+ Providers + FREE Qwen OAuth
**Use Qwen's FREE tier (2,000 req/day) with ANY Claw platform!**
**Use ANY AI provider with ANY Claw platform - including FREE Qwen tier!**
---
@@ -26,192 +26,211 @@
</div>
## ⭐ Key Feature: Qwen OAuth Cross-Platform Import
## ⭐ Two Powerful Features
```
┌─────────────────────────────────────────────────────────────────┐
│ QWEN OAUTH CROSS-PLATFORM IMPORT │
│ CLAW SETUP FEATURES │
├─────────────────────────────────────────────────────────────────┤
│ │
│ 1. Get FREE Qwen OAuth (2,000 req/day) │
│ $ qwen │
│ $ /auth → Select "Qwen OAuth" → Browser login │
│ FEATURE 1: FREE Qwen OAuth Cross-Platform Import │
│ ─────────────────────────────────────────────── │
│ ✅ FREE: 2,000 requests/day, 60 req/min │
│ ✅ Works with: OpenClaw, NanoBot, PicoClaw, ZeroClaw │
│ ✅ Model: Qwen3-Coder (coding-optimized) │
│ ✅ No API key needed - browser OAuth │
│ │
│ 2. Extract OAuth Token │
│ $ cat ~/.qwen/oauth-token.json | jq -r '.access_token' │
│ │
│ 3. Use with ANY Platform │
│ $ export OPENAI_API_KEY="$QWEN_TOKEN" │
│ $ export OPENAI_BASE_URL="https://api.qwen.ai/v1" │
│ $ export OPENAI_MODEL="qwen3-coder-plus" │
│ │
│ Then run: openclaw / nanobot / picoclaw / zeroclaw │
│ FEATURE 2: 25+ OpenCode-Compatible AI Providers │
│ ───────────────────────────────────────────── │
│ ✅ All major AI labs: Anthropic, OpenAI, Google, xAI │
│ ✅ Cloud platforms: Azure, AWS Bedrock, Google Vertex │
│ ✅ Fast inference: Groq (ultra-fast), Cerebras (fastest) │
│ ✅ Gateways: OpenRouter (100+ models), Together AI │
│ ✅ Local: Ollama, LM Studio, vLLM │
│ │
└─────────────────────────────────────────────────────────────────┘
```
## Platforms with Qwen OAuth Support
---
| Platform | Qwen OAuth | Memory | Best For |
|----------|------------|--------|----------|
| **Qwen Code** | ✅ Native | ~200MB | Coding, FREE tier |
| **OpenClaw** | ✅ Import | >1GB | Full-featured |
| **NanoBot** | ✅ Import | ~100MB | Research, Python |
| **PicoClaw** | ✅ Import | <10MB | Embedded |
| **ZeroClaw** | ✅ Import | <5MB | Performance |
| **NanoClaw** | ✅ Import | ~50MB | WhatsApp |
## Platforms Supported
## Quick Start: FREE Qwen OAuth Import
| Platform | Qwen OAuth | All Providers | Memory | Best For |
|----------|------------|---------------|--------|----------|
| **Qwen Code** | ✅ Native | ✅ | ~200MB | FREE coding |
| **OpenClaw** | ✅ Import | ✅ | >1GB | Full-featured |
| **NanoBot** | ✅ Import | ✅ | ~100MB | Research |
| **PicoClaw** | ✅ Import | ✅ | <10MB | Embedded |
| **ZeroClaw** | ✅ Import | ✅ | <5MB | Performance |
---
# FEATURE 1: FREE Qwen OAuth Import
## Quick Start (FREE)
### Step 1: Get Qwen OAuth (One-time)
```bash
# Install Qwen Code
# 1. Install Qwen Code
npm install -g @qwen-code/qwen-code@latest
# Authenticate (FREE)
# 2. Get FREE OAuth (2,000 req/day)
qwen
/auth # Select "Qwen OAuth" → Browser login with qwen.ai
# FREE: 2,000 requests/day, 60 req/min
/auth # Select "Qwen OAuth" → Browser login
# 3. Import to ANY platform
source ~/.qwen/.env && openclaw
source ~/.qwen/.env && nanobot gateway
source ~/.qwen/.env && picoclaw gateway
source ~/.qwen/.env && zeroclaw gateway
```
### Step 2: Import to Any Platform
```bash
# Extract token
export QWEN_TOKEN=$(cat ~/.qwen/oauth-token.json | jq -r '.access_token')
# Configure for OpenAI-compatible platforms
export OPENAI_API_KEY="$QWEN_TOKEN"
export OPENAI_BASE_URL="https://api.qwen.ai/v1"
export OPENAI_MODEL="qwen3-coder-plus"
# Now use with any platform!
openclaw # OpenClaw with FREE Qwen
nanobot # NanoBot with FREE Qwen
picoclaw # PicoClaw with FREE Qwen
zeroclaw # ZeroClaw with FREE Qwen
```
### Step 3: Automate with Script
```bash
# Create import script
cat > ~/import-qwen-oauth.sh << 'SCRIPT'
#!/bin/bash
export OPENAI_API_KEY=$(cat ~/.qwen/oauth-token.json | jq -r '.access_token')
export OPENAI_BASE_URL="https://api.qwen.ai/v1"
export OPENAI_MODEL="qwen3-coder-plus"
echo "✅ Qwen OAuth imported. Run your platform now."
SCRIPT
chmod +x ~/import-qwen-oauth.sh
# Usage
source ~/import-qwen-oauth.sh && openclaw
```
## Platform-Specific Setup
### OpenClaw + Qwen OAuth (FREE)
```bash
git clone https://github.com/openclaw/openclaw.git
cd openclaw && npm install
# Import Qwen OAuth
source ~/import-qwen-oauth.sh
# Or create .env
echo "OPENAI_API_KEY=$(cat ~/.qwen/oauth-token.json | jq -r '.access_token')" > .env
echo "OPENAI_BASE_URL=https://api.qwen.ai/v1" >> .env
echo "OPENAI_MODEL=qwen3-coder-plus" >> .env
npm run start
```
### NanoBot + Qwen OAuth (FREE)
```bash
pip install nanobot-ai
# Configure
cat > ~/.nanobot/config.json << CONFIG
{
"providers": {
"qwen": {
"apiKey": "$(cat ~/.qwen/oauth-token.json | jq -r '.access_token')",
"baseURL": "https://api.qwen.ai/v1"
}
},
"agents": {
"defaults": { "model": "qwen/qwen3-coder-plus" }
}
}
CONFIG
nanobot gateway
```
### ZeroClaw + Qwen OAuth (FREE)
```bash
# Install
wget https://github.com/zeroclaw-labs/zeroclaw/releases/latest/zeroclaw-linux-amd64
chmod +x zeroclaw-linux-amd64 && sudo mv zeroclaw-linux-amd64 /usr/local/bin/zeroclaw
# Import Qwen OAuth
export OPENAI_API_KEY=$(cat ~/.qwen/oauth-token.json | jq -r '.access_token')
export OPENAI_MODEL="qwen3-coder-plus"
zeroclaw gateway
```
## Qwen API Endpoints
| Endpoint | Type | Use Case |
|----------|------|----------|
| `https://api.qwen.ai/v1` | **OAuth (FREE)** | FREE 2K req/day |
| `https://dashscope.aliyuncs.com/compatible-mode/v1` | API Key | Alibaba Cloud (China) |
| `https://dashscope-intl.aliyuncs.com/compatible-mode/v1` | API Key | Alibaba Cloud (Intl) |
| `https://api-inference.modelscope.cn/v1` | API Key | ModelScope |
## Qwen Models
| Model | Context | Description |
|-------|---------|-------------|
| `qwen3-coder-plus` | 128K | **Recommended for coding** |
| `qwen3-coder-next` | 128K | Latest features |
| `qwen3.5-plus` | 128K | General purpose |
## Free Tier Limits
| Metric | Limit |
|--------|-------|
| Requests/day | 2,000 |
| Requests/day | **2,000** |
| Requests/minute | 60 |
| Cost | **FREE** |
## Usage Examples
---
# FEATURE 2: 25+ AI Providers
## FREE Tier
| Provider | Free | Model | How to Get |
|----------|------|-------|------------|
| **Qwen OAuth** | ✅ 2K/day | Qwen3-Coder | `qwen && /auth` |
## Major AI Labs
| Provider | Models | Features |
|----------|--------|----------|
| **Anthropic** | Claude 3.5/4/Opus | Extended thinking, PDF |
| **OpenAI** | GPT-4o, o1, o3, GPT-5 | Function calling |
| **Google AI** | Gemini 2.5, 3 Pro | Multimodal |
| **xAI** | Grok | Real-time data |
| **Mistral** | Large, Codestral | Code-focused |
## Cloud Platforms
| Provider | Models | Use Case |
|----------|--------|----------|
| **Azure OpenAI** | GPT-5 Enterprise | Azure integration |
| **Google Vertex** | Claude, Gemini | GCP infrastructure |
| **Amazon Bedrock** | Nova, Claude, Llama | AWS integration |
## Fast Inference
| Provider | Speed | Models |
|----------|-------|--------|
| **Groq** | Ultra-fast | Llama 3, Mixtral |
| **Cerebras** | Fastest | Llama 3 variants |
## Gateways (100+ Models)
| Provider | Models | Features |
|----------|--------|----------|
| **OpenRouter** | 100+ | Multi-provider gateway |
| **Together AI** | Open source | Fine-tuning |
| **Vercel AI** | Multi | Edge hosting |
## Local/Self-Hosted
| Provider | Use Case |
|----------|----------|
| **Ollama** | Local models |
| **LM Studio** | GUI local |
| **vLLM** | High-performance |
---
# Multi-Provider Configuration
```json
{
"providers": {
"qwen": { "type": "oauth", "free": true, "limit": 2000 },
"anthropic": { "apiKey": "${ANTHROPIC_API_KEY}" },
"openai": { "apiKey": "${OPENAI_API_KEY}" },
"google": { "apiKey": "${GOOGLE_API_KEY}" },
"groq": { "apiKey": "${GROQ_API_KEY}" },
"openrouter": { "apiKey": "${OPENROUTER_API_KEY}" },
"ollama": { "baseURL": "http://localhost:11434" }
},
"agents": {
"free": { "model": "qwen/qwen3-coder-plus" },
"premium": { "model": "anthropic/claude-sonnet-4-5" },
"fast": { "model": "groq/llama-3.3-70b-versatile" },
"local": { "model": "ollama/llama3.2:70b" }
}
}
```
---
# Quick Setup Examples
## Option 1: FREE Only
```bash
# Get FREE Qwen OAuth
npm install -g @qwen-code/qwen-code@latest
qwen && /auth
# Use with any platform
source ~/.qwen/.env && openclaw
```
## Option 2: With API Keys
```bash
# Configure providers
export ANTHROPIC_API_KEY="your-key"
export OPENAI_API_KEY="your-key"
export GOOGLE_API_KEY="your-key"
export GROQ_API_KEY="your-key"
# Or use OpenRouter for 100+ models
export OPENROUTER_API_KEY="your-key"
export OPENAI_API_KEY="$OPENROUTER_API_KEY"
export OPENAI_BASE_URL="https://openrouter.ai/api/v1"
```
## Option 3: Local Models
```bash
# Install Ollama
curl -fsSL https://ollama.com/install.sh | sh
ollama pull llama3.2:70b
# Use with Claw platforms
export OPENAI_BASE_URL="http://localhost:11434/v1"
export OPENAI_MODEL="llama3.2:70b"
```
---
# Fetch Available Models
```bash
# Use included script
./scripts/fetch-models.sh all
# Or manually
curl -s https://openrouter.ai/api/v1/models -H "Authorization: Bearer $KEY" | jq '.data[].id'
curl -s https://api.groq.com/openai/v1/models -H "Authorization: Bearer $KEY"
curl -s http://localhost:11434/api/tags
```
---
# Usage Examples
```
"Setup OpenClaw with FREE Qwen OAuth"
"Import Qwen OAuth to NanoBot for free coding"
"Configure ZeroClaw with Qwen3-Coder free tier"
"Use my Qwen free tier with any Claw platform"
```
## Troubleshooting
**Token not found?**
```bash
# Re-authenticate
qwen && /auth # Select Qwen OAuth
# Check location
ls ~/.qwen/
```
**Token expired?**
```bash
# Tokens auto-refresh - just use qwen
qwen -p "refresh"
# Re-export
source ~/import-qwen-oauth.sh
"Configure NanoBot with Anthropic and OpenAI"
"Import Qwen OAuth to ZeroClaw"
"Fetch available models from OpenRouter"
"Setup Claw with all 25+ providers"
"Add custom fine-tuned model"
```
---