Platform

Web search

Current web results with title, URL, date and a text excerpt, for your agents and your own code.

curlhttps://api.launchad.si/v1/search -d '{"query":"open-weight model releases","num_results":5}'

Fresh results. Search the live web, not a training snapshot.

Filters. Domains, start date and category.

Agent-ready. The same search as the web_search tool.

Search

Ask the web,
get clean results

One call returns ranked results with a readable excerpt, so a model can use them directly. Results are marked as untrusted content for your agents.

  • Include or exclude domains Keep results to sources you trust.

  • Date filter Only pages published after a date.

  • Categories News, research papers, GitHub, company pages and more.

POST /v1/search · 200
{ "object": "search",  "data": [{    "title": "…",    "url": "https://…",    "publishedDate": "2026-11-12"  }] }

Also included

The details
that matter

Powered by Exa

Neural and keyword search.

Rate limited per key

Same limits and headers as every API.

Up to 25 results

Per request, with text excerpts.

Untrusted by default

Agents are told not to follow page instructions.

Clear errors

503 when search is not configured, 429 when limited.

Scoped

Needs the agents scope on the key.

Related

launchad · getting started

# 1. point your OpenAI client at LaunChad
export OPENAI_BASE_URL=https://api.launchad.si/v1
export OPENAI_API_KEY=$LAUNCHAD_KEY

# 2. call any model, or start an agent run
curl $OPENAI_BASE_URL/agents/researcher/runs \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{"message":"What changed on our competitors' pricing pages?"}'

Get started

Two lines of config.
The rest is built.

Keep your OpenAI client, change the base URL and the key. Limits, logs and guardrails are on from the first request.

Free during the beta. No credit card. Launch updates only, no spam.