three.ws Concierge
nirholas/three.ws
Ask any website's AI concierge a grounded question, and generate the embed to add one to a site.
- GitHub stars
- 269
- transport
- STDIO
- env vars
- 3
- last updated
- Oct 10, 2026
Sponsors
This spot is openSlot 1$1,200/mo Advertise hereThis spot is openSlot 2$1,000/mo Advertise here
SnugSponsoredThe clipboard manager you and your agent can use, safely
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workThis spot is openSlot 6$500/mo Advertise hereThis spot is openSlot 7$500/mo Advertise here
WaxSponsoredBlock anything with supervision, without erasing your iPhone
SnugSponsoredThe clipboard manager you and your agent can use, safelyknobsSponsoredSee your site on any phone, any day, in any languageAgent CaffeineSponsoredClose your lid, come back to finished workThis spot is openSlot 6$500/mo Advertise hereThis spot is openSlot 7$500/mo Advertise hereWaxSponsoredBlock anything with supervision, without erasing your iPhoneConfiguration
THREE_WS_BASEdefault: https://three.wsBase URL of the three.ws API that serves POST /api/concierge, and the origin the generated embed snippets point at. Override only when self-hosting or targeting a preview deployment.
THREE_WS_TIMEOUT_MSdefault: 45000Per-request timeout in milliseconds for the concierge answer call. The answer streams over a free-first LLM chain that can fail over across providers, so the default leaves room for one slow rung.
CONCIERGE_PAGE_TIMEOUT_MSdefault: 12000Timeout in milliseconds for fetching a page that concierge_ask grounds its answer in. Separate from the answer timeout so a slow site cannot consume the whole call.
Readme
Details
- Repository
- github.com/nirholas/three.ws
- Website
- three.ws/concierge
- Package
@three-ws/concierge-mcp- Transport
- STDIO
- Registry
- MCP registry, active