“web search”

Provides real-time web search and article extraction through AnySearch or Tavily.

Search the web using DuckDuckGo.

Discover a bounded set of fresh web source candidates from one explicit search query, preserve provider evidence and reported cost, and prepare source…

Live web search and clean-markdown page fetch over the Keenable web index.

Keyless multi-engine web search, fetch, and clean-Markdown read for AI agents.

Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.

Search the web and get the results, in one x402 payment.

Multi-agent LLM framework for web search that runs several queries at once, with React, Gradio or Streamlit front ends.

Deep research agent that gives large reasoning models autonomous search, web browsing and report drafting.

Real-time web search API that returns ranked results as structured data, with domain, language and region filters.

Web Search API for AI applications, returning live web and news results with citations and timestamps.

Search API for developers and AI agents, built on Brave's own index without relying on Google or Bing.

Subagent "web-search-researcher" from medusajs/medusa: Do you find yourself desiring information that you don't quite feel well-trained (confident) on?

Subagent "component-researcher" from davila7/claude-code-templates: Investigates best practices and improvement opportunities for Claude Code components using…

Subagent "web" from activepieces/activepieces: Frontend agent for the Activepieces web application (packages/web).

Lightweight Python framework and starting template for agents that let the model choose its own approach to each task.

Minimal Python graph framework of about 100 lines for LLM agents, workflows, RAG and map-reduce pipelines.

All-in-one Python AI framework for embeddings-based semantic search, LLM pipelines, workflows and agents.

Builder for AI agents trained on a company's own content that answer customers, take actions and hand off to people across web, email, phone and chat apps

Retool platform for building agents that combine code, LLM decisions and human review, connected to external systems of record

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request.

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system.

Cesium2 AI — Local AI Assistant

ram1234598766

Local-first AI coding assistant powered by your own MORPH-AI Cesium2 models: streaming chat, vision, web-connected answers, cloud sessions, inline…

1,266 hard-to-find questions with short answers for testing how persistently agents can search the web.