Zero-API-Key Web Search for OpenClaw
This skill gives OpenClaw a practical verification workflow:
zero-searchfor live search results (7 engines via Bright Data)zero-search providersfor provider discoveryzero-browsefor reading pages (auto-unlocks blocked content)zero-verifyfor support/conflict classificationzero-reportfor a citation-ready summary with next stepszero-setupfor interactive provider configuration
Install
pip install zero-api-key-web-search
Minimum verification
zero-search "OpenAI API pricing" --type news --timelimit w
zero-search providers
zero-browse "https://docs.python.org/3/whatsnew/"
zero-verify "Python 3.13 is the latest stable release" --deep --max-pages 2 --json
zero-report "Python 3.13 stable release" --claim "Python 3.13 is the latest stable release" --deep --json
Provider paths
| Profile | Providers | Best for |
|---|---|---|
free | ddgs | Zero-setup local search |
free-verified | ddgs, searxng | Free cross-validation |
production | brightdata | Production reliability and geo-targeting |
production-unlock | brightdata, web_unlocker | Production SERP + blocked page access |
max-evidence | ddgs, searxng, brightdata | Maximum provider diversity |
Recommended flow
- Run
zero-searchfor factual or recent questions. - Use
zero-browseon the most relevant source when snippets are not enough. - Use
zero-verifywhen a concrete claim needs a support/conflict summary. - Use
zero-reportwhen you want a compact evidence package with citations and next steps. - Use
--deepwhen the claim matters enough to justify page-aware verification. - Cite the returned URLs in the final answer.
- Use optional
brightdataonly when configured or explicitly requested.
Multi-engine search (Bright Data)
zero-search "AI regulation" --provider brightdata --engine google --region us-en --json
zero-search "AI regulation" --provider brightdata --engine bing --region gb-en --json
zero-search "news" --provider brightdata --engine yandex --region ru-ru --json
Supported engines: google, bing, duckduckgo, yandex, baidu, yahoo, naver.
Web Unlocker (blocked pages)
# Auto-fallback (default) — direct fetch, then unlocker on 403/429
zero-browse "https://protected-site.com/article"
# Force Web Unlocker
zero-browse "https://protected-site.com/article" --use-unlocker always
Optional Bright Data provider
# Interactive setup wizard
zero-setup
# Or set environment variables
export ZERO_SEARCH_BRIGHTDATA_API_KEY="..."
export ZERO_SEARCH_BRIGHTDATA_ZONE="serp_api1"
export ZERO_SEARCH_BRIGHTDATA_UNLOCKER_ZONE="web_unlocker1"
New Bright Data users can sign up at https://get.brightdata.com/h21j9xz4uxgd.
What success looks like
- the verdict is explicit
- the result includes support and conflict scores
page_awareis true when deep verification ran- the recommended free path is
ddgs + self-hosted searxng - optional production path is
brightdata + web_unlockerviaZERO_SEARCH_BRIGHTDATA_API_KEY - source URLs are ready to cite
Limits
zero-verifyis heuristic and evidence-aware, not a proof engine.- The default provider path is
ddgs. - The recommended free upgrade path is self-hosted
searxngviaZERO_SEARCH_SEARXNG_URL. - Bright Data is optional and should not receive queries unless configured or requested.
- Conflicting sources are surfaced, not automatically reconciled.
License
MIT License.