\r \r

OpenClaw Search 🔍\r

\r Intelligent search for autonomous agents. Powered by AIsa.\r \r One API key. Multi-source retrieval. Confidence-scored answers.\r \r

Inspired by AIsa Verity - A next-generation search agent with trust-scored answers.\r \r

🔥 What Can You Do?\r

\r

Research Assistant\r

"Search for the latest papers on transformer architectures from 2024-2025"\r
```\r
\r
### Market Research\r
```\r
"Find all web articles about AI startup funding in Q4 2025"\r
```\r
\r
### Competitive Analysis\r
```\r
"Search for reviews and comparisons of RAG frameworks"\r
```\r
\r
### News Aggregation\r
```\r
"Get the latest news about quantum computing breakthroughs"\r
```\r
\r
### Deep Dive Research\r
```\r
"Smart search combining web and academic sources on 'autonomous agents'"\r
```\r
\r
## Quick Start\r
\r
```bash\r
export AISA_API_KEY="your-key"\r
```\r
\r
---\r
\r
## 🏗️ Architecture: Multi-Stage Orchestration\r
\r
OpenClaw Search employs a **Two-Phase Retrieval Strategy** for comprehensive results:\r
\r
### Phase 1: Discovery (Parallel Retrieval)\r
\r
Query 4 distinct search streams simultaneously:\r
- **Scholar**: Deep academic retrieval\r
- **Web**: Structured web search\r
- **Smart**: Intelligent mixed-mode search\r
- **Tavily**: External validation signal\r
\r
### Phase 2: Reasoning (Meta-Analysis)\r
\r
Use **AIsa Explain** to perform meta-analysis on search results, generating:\r
- Confidence scores (0-100)\r
- Source agreement analysis\r
- Synthesized answers\r
\r
```\r
┌─────────────────────────────────────────────────────────────┐\r
│                      User Query                              │\r
└─────────────────────────────────────────────────────────────┘\r
                              │\r
              ┌───────────────┼───────────────┐\r
              ▼               ▼               ▼\r
        ┌─────────┐     ┌─────────┐     ┌─────────┐\r
        │ Scholar │     │   Web   │     │  Smart  │\r
        └─────────┘     └─────────┘     └─────────┘\r
              │               │               │\r
              └───────────────┼───────────────┘\r
                              ▼\r
                    ┌─────────────────┐\r
                    │  AIsa Explain   │\r
                    │ (Meta-Analysis) │\r
                    └─────────────────┘\r
                              │\r
                              ▼\r
                    ┌─────────────────┐\r
                    │ Confidence Score│\r
                    │  + Synthesis    │\r
                    └─────────────────┘\r
```\r
\r
---\r
\r
## Core Capabilities\r
\r
### Web Search\r
\r
```bash\r
# Basic web search\r
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/web?query=AI+frameworks&max_num_results=10" \\r
  -H "Authorization: Bearer $AISA_API_KEY"\r
\r
# Full text search (with page content)\r
curl -X POST "https://api.aisa.one/apis/v1/search/full?query=latest+AI+news&max_num_results=10" \\r
  -H "Authorization: Bearer $AISA_API_KEY"\r
```\r
\r
### Academic/Scholar Search\r
\r
```bash\r
# Search academic papers\r
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/scholar?query=transformer+models&max_num_results=10" \\r
  -H "Authorization: Bearer $AISA_API_KEY"\r
\r
# With year filter\r
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/scholar?query=LLM&max_num_results=10&as_ylo=2024&as_yhi=2025" \\r
  -H "Authorization: Bearer $AISA_API_KEY"\r
```\r
\r
### Smart Search (Web + Academic Combined)\r
\r
```bash\r
# Intelligent hybrid search\r
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/smart?query=machine+learning+optimization&max_num_results=10" \\r
  -H "Authorization: Bearer $AISA_API_KEY"\r
```\r
\r
### Tavily Integration (Advanced)\r
\r
```bash\r
# Tavily search\r
curl -X POST "https://api.aisa.one/apis/v1/tavily/search" \\r
  -H "Authorization: Bearer $AISA_API_KEY" \\r
  -H "Content-Type: application/json" \\r
  -d '{"query":"latest AI developments"}'\r
\r
# Extract content from URLs\r
curl -X POST "https://api.aisa.one/apis/v1/tavily/extract" \\r
  -H "Authorization: Bearer $AISA_API_KEY" \\r
  -H "Content-Type: application/json" \\r
  -d '{"urls":["https://example.com/article"]}'\r
\r
# Crawl web pages\r
curl -X POST "https://api.aisa.one/apis/v1/tavily/crawl" \\r
  -H "Authorization: Bearer $AISA_API_KEY" \\r
  -H "Content-Type: application/json" \\r
  -d '{"url":"https://example.com","max_depth":2}'\r
\r
# Site map\r
curl -X POST "https://api.aisa.one/apis/v1/tavily/map" \\r
  -H "Authorization: Bearer $AISA_API_KEY" \\r
  -H "Content-Type: application/json" \\r
  -d '{"url":"https://example.com"}'\r
```\r
\r
### Explain Search Results (Meta-Analysis)\r
\r
```bash\r
# Generate explanations with confidence scoring\r
curl -X POST "https://api.aisa.one/apis/v1/scholar/explain" \\r
  -H "Authorization: Bearer $AISA_API_KEY" \\r
  -H "Content-Type: application/json" \\r
  -d '{"results":[...],"language":"en","format":"summary"}'\r
```\r
\r
---\r
\r
## 📊 Confidence Scoring Engine\r
\r
Unlike standard RAG systems, OpenClaw Search evaluates credibility and consensus:\r
\r
### Scoring Rubric\r
\r
| Factor | Weight | Description |\r
|--------|--------|-------------|\r
| **Source Quality** | 40% | Academic > Smart/Web > External |\r
| **Agreement Analysis** | 35% | Cross-source consensus checking |\r
| **Recency** | 15% | Newer sources weighted higher |\r
| **Relevance** | 10% | Query-result semantic match |\r
\r
### Score Interpretation\r
\r
| Score | Confidence Level | Meaning |\r
|-------|-----------------|---------|\r
| 90-100 | Very High | Strong consensus across academic and web sources |\r
| 70-89 | High | Good agreement, reliable sources |\r
| 50-69 | Medium | Mixed signals, verify independently |\r
| 30-49 | Low | Conflicting sources, use caution |\r
| 0-29 | Very Low | Insufficient or contradictory data |\r
\r
---\r
\r
## Python Client\r
\r
```bash\r
# Web search\r
python3 {baseDir}/scripts/search_client.py web --query "latest AI news" --count 10\r
\r
# Academic search\r
python3 {baseDir}/scripts/search_client.py scholar --query "transformer architecture" --count 10\r
python3 {baseDir}/scripts/search_client.py scholar --query "LLM" --year-from 2024 --year-to 2025\r
\r
# Smart search (web + academic)\r
python3 {baseDir}/scripts/search_client.py smart --query "autonomous agents" --count 10\r
\r
# Full text search\r
python3 {baseDir}/scripts/search_client.py full --query "AI startup funding"\r
\r
# Tavily operations\r
python3 {baseDir}/scripts/search_client.py tavily-search --query "AI developments"\r
python3 {baseDir}/scripts/search_client.py tavily-extract --urls "https://example.com/article"\r
\r
# Multi-source search with confidence scoring\r
python3 {baseDir}/scripts/search_client.py verity --query "Is quantum computing ready for enterprise?"\r
```\r
\r
---\r
\r
## API Endpoints Reference\r
\r
| Endpoint | Method | Description |\r
|----------|--------|-------------|\r
| `/scholar/search/web` | POST | Web search with structured results |\r
| `/scholar/search/scholar` | POST | Academic paper search |\r
| `/scholar/search/smart` | POST | Intelligent hybrid search |\r
| `/scholar/explain` | POST | Generate result explanations |\r
| `/search/full` | POST | Full text search with content |\r
| `/search/smart` | POST | Smart web search |\r
| `/tavily/search` | POST | Tavily search integration |\r
| `/tavily/extract` | POST | Extract content from URLs |\r
| `/tavily/crawl` | POST | Crawl web pages |\r
| `/tavily/map` | POST | Generate site maps |\r
\r
---\r
\r
## Search Parameters\r
\r
| Parameter | Type | Description |\r
|-----------|------|-------------|\r
| query | string | Search query (required) |\r
| max_num_results | integer | Max results (1-100, default 10) |\r
| as_ylo | integer | Year lower bound (scholar only) |\r
| as_yhi | integer | Year upper bound (scholar only) |\r
\r
---\r
\r
## 🚀 Building a Verity-Style Agent\r
\r
Want to build your own confidence-scored search agent? Here's the pattern:\r
\r
### 1. Parallel Discovery\r
\r
```python\r
import asyncio\r
\r
async def discover(query):\r
    """Phase 1: Parallel retrieval from multiple sources."""\r
    tasks = [\r
        search_scholar(query),\r
        search_web(query),\r
        search_smart(query),\r
        search_tavily(query)\r
    ]\r
    results = await asyncio.gather(*tasks)\r
    return {\r
        "scholar": results[0],\r
        "web": results[1],\r
        "smart": results[2],\r
        "tavily": results[3]\r
    }\r
```\r
\r
### 2. Confidence Scoring\r
\r
```python\r
def score_confidence(results):\r
    """Calculate deterministic confidence score."""\r
    score = 0\r
    \r
    # Source quality (40%)\r
    if results["scholar"]:\r
        score += 40 * len(results["scholar"]) / 10\r
    \r
    # Agreement analysis (35%)\r
    claims = extract_claims(results)\r
    agreement = analyze_agreement(claims)\r
    score += 35 * agreement\r
    \r
    # Recency (15%)\r
    recency = calculate_recency(results)\r
    score += 15 * recency\r
    \r
    # Relevance (10%)\r
    relevance = calculate_relevance(results, query)\r
    score += 10 * relevance\r
    \r
    return min(100, score)\r
```\r
\r
### 3. Synthesis\r
\r
```python\r
async def synthesize(query, results, score):\r
    """Generate final answer with citations."""\r
    explanation = await explain_results(results)\r
    return {\r
        "answer": explanation["summary"],\r
        "confidence": score,\r
        "sources": explanation["citations"],\r
        "claims": explanation["claims"]\r
    }\r
```\r
\r
For a complete implementation, see [AIsa Verity](https://github.com/AIsa-team/verity).\r
\r
---\r
\r
## Pricing\r
\r
| API | Cost |\r
|-----|------|\r
| Web search | ~$0.001 |\r
| Scholar search | ~$0.002 |\r
| Smart search | ~$0.002 |\r
| Tavily search | ~$0.002 |\r
| Explain | ~$0.003 |\r
\r
Every response includes `usage.cost` and `usage.credits_remaining`.\r
\r
---\r
\r
## Get Started\r
\r
1. Sign up at [aisa.one](https://aisa.one)\r
2. Get your API key\r
3. Add credits (pay-as-you-go)\r
4. Set environment variable: `export AISA_API_KEY="your-key"`\r
\r
## Full API Reference\r
\r
See [API Reference](https://aisa.mintlify.app/api-reference/introduction) for complete endpoint documentation.\r
\r
## Resources\r
\r
- [AIsa Verity](https://github.com/AIsa-team/verity) - Reference implementation of confidence-scored search agent\r
- [AIsa Documentation](https://aisa.mintlify.app) - Complete API documentation\r