unsearchSearch the web, scrape content, and conduct deep research using the UnSearch API. Use when the user needs real-time web search results, content extraction from URLs, fact verification, or multi-source research for AI agents, RAG pipelines, or LLM applications.
Install via ClawdBot CLI:
clawdbot install Rakesh1002/unsearchGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://api.unsearch.dev/api/v1/searchCalls external URL not in known-safe list
https://unsearch.devAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
A media startup uses UnSearch's web search and content extraction to automatically gather and summarize breaking news from multiple sources in real-time. This enables rapid content creation for newsletters or AI-generated news briefs, ensuring up-to-date coverage without manual research.
A tech consultancy employs UnSearch's deep research and fact verification to analyze competitor landscapes and validate market trends for clients. This provides data-driven insights for strategic planning, reducing research time from days to hours while improving accuracy.
An e-learning platform integrates UnSearch to verify facts and sources in course materials, ensuring educational content is accurate and up-to-date. This helps maintain credibility and compliance with academic standards, automating quality checks for instructors.
A healthcare tech company uses UnSearch's agent search and deep research to build AI assistants that provide evidence-based medical information to professionals. This supports diagnostic tools or patient education by synthesizing research from trusted sources quickly.
A legal firm leverages UnSearch to extract and verify information from online sources for case preparation, such as checking precedents or gathering public records. This streamlines due diligence and enhances argumentation with reliable, multi-source data.
Offer tiered subscription plans based on query volume (e.g., free tier with 5,000 queries/month, paid tiers for higher limits). This generates recurring revenue from developers, AI startups, and enterprises integrating UnSearch into their applications.
Provide customized, branded versions of UnSearch for large corporations needing internal research tools or customer-facing applications. This includes dedicated support and integration services, targeting sectors like finance or healthcare.
Implement a usage-based pricing model where clients pay per query or data processed, ideal for research firms or academic institutions with fluctuating needs. This offers flexibility and scalability, attracting users who avoid fixed subscriptions.
💬 Integration Tip
Start by setting the UNSEARCH_API_KEY environment variable and test with the web search endpoint using a simple query to verify connectivity before scaling to advanced features like deep research.
Scored May 17, 2026
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
Multi search engine integration with 16 engines (7 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and Wolfra...
AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources.
Web search via Tavily API (alternative to Brave). Use when the user asks to search the web / look up sources / find links and Brave web_search is unavailable...
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.