OpenClaw Search 🔍

Intelligent search for autonomous agents. Powered by AIsa.

One API key. Multi-source retrieval. Confidence-scored answers.

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

🔥 What Can You Do?

Research Assistant

"Search for the latest papers on transformer architectures from 2024-2025"

Market Research

"Find all web articles about AI startup funding in Q4 2025"

Competitive Analysis

"Search for reviews and comparisons of RAG frameworks"

News Aggregation

"Get the latest news about quantum computing breakthroughs"

Deep Dive Research

"Smart search combining web and academic sources on 'autonomous agents'"

Quick Start

export AISA_API_KEY="your-key"

🏗️ Architecture: Multi-Stage Orchestration

OpenClaw Search employs a Two-Phase Retrieval Strategy for comprehensive results:

Phase 1: Discovery (Parallel Retrieval)

Query 4 distinct search streams simultaneously:

• Scholar: Deep academic retrieval
• Web: Structured web search
• Smart: Intelligent mixed-mode search
• Tavily: External validation signal

Phase 2: Reasoning (Meta-Analysis)

Use AIsa Explain to perform meta-analysis on search results, generating:

• Confidence scores (0-100)
• Source agreement analysis
• Synthesized answers

┌─────────────────────────────────────────────────────────────┐
│                      User Query                              │
└─────────────────────────────────────────────────────────────┘
                              │
              ┌───────────────┼───────────────┐
              ▼               ▼               ▼
        ┌─────────┐     ┌─────────┐     ┌─────────┐
        │ Scholar │     │   Web   │     │  Smart  │
        └─────────┘     └─────────┘     └─────────┘
              │               │               │
              └───────────────┼───────────────┘
                              ▼
                    ┌─────────────────┐
                    │  AIsa Explain   │
                    │ (Meta-Analysis) │
                    └─────────────────┘
                              │
                              ▼
                    ┌─────────────────┐
                    │ Confidence Score│
                    │  + Synthesis    │
                    └─────────────────┘

Core Capabilities

Web Search

# Basic web search
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/web?query=AI+frameworks&max_num_results=10" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Full text search (with page content)
curl -X POST "https://api.aisa.one/apis/v1/search/full?query=latest+AI+news&max_num_results=10" \
  -H "Authorization: Bearer $AISA_API_KEY"

Academic/Scholar Search

# Search academic papers
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/scholar?query=transformer+models&max_num_results=10" \
  -H "Authorization: Bearer $AISA_API_KEY"

# With year filter
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/scholar?query=LLM&max_num_results=10&as_ylo=2024&as_yhi=2025" \
  -H "Authorization: Bearer $AISA_API_KEY"

Smart Search (Web + Academic Combined)

# Intelligent hybrid search
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/smart?query=machine+learning+optimization&max_num_results=10" \
  -H "Authorization: Bearer $AISA_API_KEY"

Tavily Integration (Advanced)

# Tavily search
curl -X POST "https://api.aisa.one/apis/v1/tavily/search" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"latest AI developments"}'

# Extract content from URLs
curl -X POST "https://api.aisa.one/apis/v1/tavily/extract" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"urls":["https://example.com/article"]}'

# Crawl web pages
curl -X POST "https://api.aisa.one/apis/v1/tavily/crawl" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com","max_depth":2}'

# Site map
curl -X POST "https://api.aisa.one/apis/v1/tavily/map" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com"}'

Explain Search Results (Meta-Analysis)

# Generate explanations with confidence scoring
curl -X POST "https://api.aisa.one/apis/v1/scholar/explain" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"results":[...],"language":"en","format":"summary"}'

📊 Confidence Scoring Engine

Unlike standard RAG systems, OpenClaw Search evaluates credibility and consensus:

Scoring Rubric

Score Interpretation

Python Client

# Web search
python3 {baseDir}/scripts/search_client.py web --query "latest AI news" --count 10

# Academic search
python3 {baseDir}/scripts/search_client.py scholar --query "transformer architecture" --count 10
python3 {baseDir}/scripts/search_client.py scholar --query "LLM" --year-from 2024 --year-to 2025

# Smart search (web + academic)
python3 {baseDir}/scripts/search_client.py smart --query "autonomous agents" --count 10

# Full text search
python3 {baseDir}/scripts/search_client.py full --query "AI startup funding"

# Tavily operations
python3 {baseDir}/scripts/search_client.py tavily-search --query "AI developments"
python3 {baseDir}/scripts/search_client.py tavily-extract --urls "https://example.com/article"

# Multi-source search with confidence scoring
python3 {baseDir}/scripts/search_client.py verity --query "Is quantum computing ready for enterprise?"

API Endpoints Reference

/scholar/search/web

/scholar/search/scholar

/scholar/search/smart

/scholar/explain

/search/full

/search/smart

/tavily/search

/tavily/extract

/tavily/crawl

/tavily/map

Search Parameters

🚀 Building a Verity-Style Agent

Want to build your own confidence-scored search agent? Here's the pattern:

1. Parallel Discovery

import asyncio

async def discover(query):
    """Phase 1: Parallel retrieval from multiple sources."""
    tasks = [
        search_scholar(query),
        search_web(query),
        search_smart(query),
        search_tavily(query)
    ]
    results = await asyncio.gather(*tasks)
    return {
        "scholar": results[0],
        "web": results[1],
        "smart": results[2],
        "tavily": results[3]
    }

2. Confidence Scoring

def score_confidence(results):
    """Calculate deterministic confidence score."""
    score = 0
    
    # Source quality (40%)
    if results["scholar"]:
        score += 40 * len(results["scholar"]) / 10
    
    # Agreement analysis (35%)
    claims = extract_claims(results)
    agreement = analyze_agreement(claims)
    score += 35 * agreement
    
    # Recency (15%)
    recency = calculate_recency(results)
    score += 15 * recency
    
    # Relevance (10%)
    relevance = calculate_relevance(results, query)
    score += 10 * relevance
    
    return min(100, score)

3. Synthesis

async def synthesize(query, results, score):
    """Generate final answer with citations."""
    explanation = await explain_results(results)
    return {
        "answer": explanation["summary"],
        "confidence": score,
        "sources": explanation["citations"],
        "claims": explanation["claims"]
    }

For a complete implementation, see AIsa Verity.

Pricing

Every response includes

usage.cost

usage.credits_remaining

Get Started

1. Sign up at aisa.one
2. Get your API key
3. Add credits (pay-as-you-go)
4. Set environment variable:

   export AISA_API_KEY="your-key"

Full API Reference

See API Reference for complete endpoint documentation.

Resources

• AIsa Verity - Reference implementation of confidence-scored search agent
• AIsa Documentation - Complete API documentation