Install
openclaw skills install tavily-plusEnhanced Tavily search with multi-API key rotation, AI-powered intent recognition, sub-question decomposition, intelligent summarization, and offline document export. Use when user needs intelligent web search with auto-failover, research workflows, or downloadable reports.
openclaw skills install tavily-plusEnhanced search skill with AI augmentation and multiple API keys.
| Tool | Description |
|---|---|
smart_search | AI-enhanced search with intent recognition, sub-question breakdown, and smart routing |
tavily_search | Standard Tavily search (fallback/legacy mode) |
tavily_extract | URL content extraction |
Configure in plugins.entries.tavily.config.webSearch:
{
"apiKey": {
"key1": "tvly-xxx1",
"key2": "tvly-xxx2"
},
"baseUrl": "https://api.tavily.com"
}
Or via env: TAVILY_API_KEY, TAVILY_API_KEY_2, TAVILY_API_KEY_N
AI-augmented search that performs:
| Parameter | Type | Description |
|---|---|---|
query | string | Natural language search query |
mode | string | research (deep), quick (basic), compare (multiple) |
max_results | number | Results per sub-query (1-20) |
include_answer | boolean | Include AI summary (default: true) |
export_doc | boolean | Generate offline markdown report |
sub_questions | array | Optional pre-defined sub-queries (bypasses decomposition) |
| Mode | Behavior |
|---|---|
research | Deep search with multiple sub-queries, high max_results |
quick | Single-pass basic search |
compare | Multi-perspective search for comparisons |
{
"intent": "research",
"sub_questions": ["...", "..."],
"search_results": [...],
"summary": "...",
"doc_path": "/path/to/report.md" // if export_doc=true
}
plugins.entries.tavily.config.webSearch.apiKey (object with multiple keys)TAVILY_API_KEY, TAVILY_API_KEY_2, ..., TAVILY_API_KEY_NSupported intent types:
factual - Direct answer queries (who, what, when, where)how_to - Procedural instructionscomparison - A vs B analysisresearch - In-depth information gatheringnews - Current eventsopinion - Perspectives and opinionsWhen export_doc: true:
~/.openclaw/workspace/reports/tavily-plus-{timestamp}.mddoc_path in responseUser Query
↓
Intent Recognition (LLM)
↓
Sub-question Decomposition (LLM)
↓
For each sub-question:
├─ Query Tavily (key rotation on 429)
└─ Collect results
↓
Intelligent Summarization (LLM)
↓
[Optional] Generate Offline Report
↓
Return Enhanced Response