🌿 laurel

Web context for LLMs,
without the bill.

One API call: search the web, get top results and clean Markdown excerpts your model can cite. Cached, categorized, and priced in micro-cents.

Start free
curl -X POST https://laurel-production-5151.up.railway.app/search \
  -H "Authorization: Bearer lrl_..." \
  -H "Content-Type: application/json" \
  -d '{"q": "is fastify worth it", "fetch_pages": 1}'

Source-backed answers

Top-10 results with snippets, plus main-content Markdown excerpts of the top pages — ready to drop into an LLM prompt.

Smart routing

Queries are auto-classified — news, community, developer, research, factual, local — and routed to the engines that answer them best.

Ultra cost effective

Cache-first responses, minimal engine fan-out, hard limits on everything. Per-request cost telemetry down to fractions of a cent.