Skip to main content
View on GitHub → Web search and page extraction through AIsa. Find current sources or turn public URLs into readable content with Tavily-backed endpoints.

​
Install

Start a new agent session after installing so the skill loads.

​
What can agents do with it?

Source discovery

Find credible sources for a topic or question.

News lookup

Search current web results for recent context.

Page extraction

Extract readable text from public URLs.

Research workflows

Gather sources before writing a brief or report.

​
When to use

  • When the user needs web search results for a topic, question, company, product, or event
  • When the user wants source discovery before summarizing, comparing, or validating information
  • When the user needs current-news lookup with recent-day filtering
  • When the user provides a public URL and wants the page content extracted for downstream analysis

​
When NOT to use

  • Do not use this skill for sites that require login, browser interaction, cookies, or private account access
  • Do not use this skill for posting, social engagement, media upload, or OAuth-based workflows; it performs search and public-URL extraction only
  • Do not use this skill when there is no network access to https://aisa.one or https://api.aisa.one

​
Quick Reference

​
Capabilities

  • Search the web through AIsa’s Tavily-backed relay
  • Return concise, relevant result sets for research and agent workflows
  • Run deeper research with --deep for broader coverage
  • Focus on news search with --topic news
  • Limit news lookback windows with --days <n>
  • Extract readable content from a public URL

​
Options

  • -n <count>: Number of results (default: 5, max: 20)
  • --deep: Use advanced search for deeper research (slower, more comprehensive)
  • --topic <topic>: Search topic - general (default) or news
  • --days <n>: For news topic, limit to last n days

​
Extract content from URL

​
Setup

Requirements:
  • node
  • AISA_API_KEY
  • Internet access with outbound requests to https://aisa.one and https://api.aisa.one
Auth, relay, and side-effect notes:
  • This skill requires AISA_API_KEY from https://console.aisa.one
  • Requests are sent through AIsa’s remote relay at https://aisa.one and https://api.aisa.one
  • This skill does not use OAuth
  • This skill does not upload media or files
  • This skill may send user search queries and public target URLs to the remote AIsa relay in order to return search results or extracted content

​
Example Requests

  • “Search for recent coverage of OpenAI enterprise pricing”
  • “Find sources comparing vector databases for production RAG”
  • “Look up this week’s news about NVIDIA export controls”
  • “Extract the main content from this article URL”

​
Notes

  • Needs AISA_API_KEY from https://console.aisa.one
  • Powered by AIsa’s unified API gateway (https://aisa.one / https://api.aisa.one)
  • Use --deep for complex research questions
  • Use --topic news for current events
  • Search and extraction operate through remote relay requests, not local browser automation

​
Get started

  1. Sign up at aisa.one and create an API key in the console.
  2. Set it in your shell: export AISA_API_KEY="your-key".
  3. Install the skill with one of the commands under Install, then start a new agent session.

Tavily Search

Focused Tavily search with filters and depth controls.

Tavily Extract

Extract clean readable content from URLs.

Multi-source Search

Combine Tavily with scholar and Perplexity.