[06] Web grounding/ What it knows

Web grounding for AI agents

Live information from outside your walls, in a shape a model can read.

5 options tracked · 2 open source · 2 self-hostable · optional

· All 5 options/ Compare
OptionWhat it doesLicenceSelf-host
ExaEmbeddings-native web search built for agents, with full-content retrieval.ProprietaryNo
TavilySearch API that returns model-ready answers rather than ten blue links.ProprietaryNo
FirecrawlTurns any site into clean markdown, including the JavaScript-heavy ones.Open sourceYes
Brave Search APIIndependent web index with straightforward per-query pricing.ProprietaryNo
SearXNGSelf-hosted metasearch. No third-party search vendor in the path.Open sourceYes
· Head to head/ 10 comparisons
· Common questions/ FAQ

What is the web grounding layer of an AI agent?

Live information from outside your walls, in a shape a model can read. It is optional; plenty of working agents skip it.

How many web grounding options are there?

This registry tracks 5. 2 are open source and 2 can run on your own infrastructure.

Which web grounding option should I choose?

It depends on constraints rather than preference: whether you must self-host, whether the budget allows a hosted service, and which language your team writes. Describe what you are building and the advisor fills this layer along with the other 9.

· The other 9 layers/ Keep going
· For agents/ This page, machine-readable

Every page here answers to Accept: text/markdown and returns the same content at roughly a tenth the tokens. No separate site, no toggle — same URL.

curl -s -H "Accept: text/markdown" https://newagent.build/layers/search