← all tools
Data & sourcing

BuiltWith

Find every company running the technology you recruit for.

BuiltWith is a data and sourcing tool, and one of the 53 tools hyreflow connects to Claude, ChatGPT and other AI assistants. Through hyreflow, an AI agent can run 9 actions, all of which look something up. BuiltWith runs on your own BuiltWith account: hyreflow charges no credits for it, and BuiltWith bills you as before.

Cost per callBYOK · vendor billed
Your own keyrequired
CategoryData & sourcing

BuiltWith knows what software a website is built on. Ask who uses React, Kubernetes or Salesforce and you get the companies that need people who know it. Point it at one company instead and you get their whole stack, which tells you whether your candidate fits.

BuiltWith pairs with GitHub on technical roles. One finds the companies on a stack, the other finds the engineers who know it.

What can you ask Claude or ChatGPT to do with BuiltWith?

With hyreflow connected, you ask for the outcome in plain language and the assistant runs BuiltWith for you. For example:

  • “Which UK companies use Kubernetes, and which of them are hiring for it per TheirStack?”
  • “What is this company built on, and does this candidate's stack match?”
  • “Find firms running Salesforce, then source their admins through Apollo”
  • “Take this list and have hyreflow Agent rank it against my ICP”

Which tools work well with BuiltWith?

In a hyreflow run, BuiltWith is most often paired with TheirStack, GitHub, Apollo and hyreflow Agent.

  • TheirStack

    a stack plus a live role beats either signal alone

  • GitHub

    the engineer side of the same technical signal

  • Apollo

    names inside the companies running that stack

  • hyreflow Agent

    score a long company list without reading it

Which BuiltWith actions can an AI agent run through hyreflow?

Through hyreflow, an AI agent can run 9 BuiltWith actions, all of which look something up. BuiltWith runs on your own BuiltWith account: hyreflow charges no credits for it, and BuiltWith bills you as before.

BuiltWith actionWhat it doesCost through hyreflow
Vector searchLooks something upno hyreflow credits
CategoriesLooks something upno hyreflow credits
Company to URLLooks something upno hyreflow credits
DomainLooks something upno hyreflow credits
FreeLooks something upno hyreflow credits
KeywordsLooks something upno hyreflow credits
ListsLooks something upno hyreflow credits
RelationshipsLooks something upno hyreflow credits
TrendsLooks something upno hyreflow credits

One credit is priced on the pricing page. The full price list for every tool is in the pricing tables.

How does an AI agent know how to use BuiltWith?

hyreflow ships a written playbook for BuiltWith, and the agent loads it before the first call. Auth, rate limits, what each call costs, which actions need your approval, and the mistakes worth avoiding. It is the difference between an agent that knows the tool and one that guesses at it.

Read the BuiltWith docs →
Show the raw playbookwritten for the agent

HOW in lib/builtwith.py. Index: reference/docs/builtwith/raw/endpoints.md.

Auth & config

  • Host: https://api.builtwith.com · Auth: KEY query param (env BUILTWITH_API_KEY; auto-injected by the client; never hardcode).
  • Each API is separately versioned (Domain v22, Lists12, rv4, free1, Trends v6, ctu3, kw2). Credit/quota-metered per plan — Lists is the heavy one.
  • BYOK-only — each workspace connects its own BuiltWith key in Integrations. Connecting your own key needs the Essential plan or above.

Operations

  • domain(lookup) — full tech profile of a site. lists(tech) / iter_lists(tech) — sites using a technology (the sourcing endpoint; paginated via OFFSET/NextOffset). company_to_url(company) — name→domain. trends(tech) — adoption over time. relationships(lookup), keywords(lookup), free(lookup) (light/safe pilot). Anything else → request().

Recruiter use (why it's here)

  • lists(tech) = source companies by stack — "who uses React / Kubernetes / Salesforce / Shopify" → those companies hire for that stack (IT-recruiting BD + candidate-company targeting). Heavy/credit-costly: pilot small, page with iter_lists(max_records=…).
  • domain(domain) = qualify/enrich one company by tech — match a company's stack to a candidate's skills, or qualify an ICP by required tech (e.g. "uses Go + Kubernetes").
  • company_to_url(name) resolves a sponsor/company to its domain before domain.

Handoff

Sourcing/qualification (IT): lists(tech) → companies on a stack → qualify vs ICP → find hiring managers (people-search) → enrich → outreach/ATS. Or enrich a known company's stack with domain to sharpen targeting. Pairs with [[github]] (the dev-side signal) for technical roles.

Callable surface — lib/builtwith.py

Import: from lib.builtwith import BuiltWith → instantiate BuiltWith() (reads key from env). Base: https://api.builtwith.com. Generic passthrough: request(method, path, *, params, json).

  • categories(**params) -> Any — GET /v22/api.json?CATEGORIES=1 — lookup table: the full list of every technology category/group BuiltWith tracks. CONFIRMED api.builtwith.com 2026-06-01.
  • company_to_url(company: str, **params) -> Any — GET /ctu3/api.json?COMPANY={name} — resolve a company name → domain (feed domain).
  • credit_balance() -> Any — GET payments.builtwith.com/v1/billing/api-discovery — prepaid Agent-API credit pool: {credits_total, credits_used, credits_available} on the caller's own BuiltWith account (BuiltWith is BYOK-only). Requires "Agent API Billing" enabled on the account. Doc: api.builtwith.com/agent-payment-api.
  • domain(lookup: str, **params) -> Any — GET /v22/api.json?LOOKUP={domain} — full tech profile of a domain (qualify/enrich by tech stack).
  • free(lookup: str, **params) -> Any — GET /free1/api.json?LOOKUP={domain} — free-tier basic tech lookup (light; safe pilot).
  • iter_lists(tech: str, *, max_records: int = 1000, **params) -> Iterator[dict] — Walk Lists API pages via NextOffset (bounded by max_records). Field/offset names follow the Lists API response — verify on first pilot; falls back gracefully if absent.
  • keywords(lookup: str, **params) -> Any — GET /kw2/api.json?LOOKUP={domain} — keywords associated with a domain.
  • lists(tech: str, **params) -> Any — GET /lists12/api.json?TECH={tech} — companies/sites using a technology (the sourcing endpoint).
  • relationships(lookup: str, **params) -> Any — GET /rv4/api.json?LOOKUP={domain} — sites sharing relationships (shared trackers/IDs).
  • trends(tech: str, **params) -> Any — GET /trends/v6/api.json?TECH={tech} — adoption trend (usage over time) for a technology.
  • vector_search(query: str, *, limit: int = 10, **params) -> Any — GET /vector/v1/api.json?QUERY={text}&LIMIT={n} — semantic search over BuiltWith's technology + category catalog. THE way to discover valid TECH values: pass a plain-text query ("applicant tracking", "react framework"), get back results with Name (the exact token to pass to lists()/trends()), Type ("tech"|"category"), Tag, and Score.

Questions about BuiltWith and hyreflow

Can I use BuiltWith inside Claude or ChatGPT?

Yes. hyreflow is a connector for Claude, ChatGPT and other AI assistants. Once hyreflow is connected, you ask for the outcome in plain language and the assistant calls BuiltWith for you. hyreflow exposes 9 BuiltWith actions this way.

Do I need my own BuiltWith account to use it with hyreflow?

Yes. BuiltWith runs on your own BuiltWith account. You connect it to hyreflow once, hyreflow charges no credits for the calls, and BuiltWith bills you as before.

What does BuiltWith cost through hyreflow?

BuiltWith runs on your own BuiltWith account: hyreflow charges no credits for it, and BuiltWith bills you as before.

How do I connect BuiltWith to an AI agent over MCP?

Add the hyreflow MCP server to your assistant and sign in. hyreflow calls the BuiltWith API directly and exposes its actions as tools the assistant can run, so there is no separate BuiltWith server to install.

Connect hyreflow to your assistant →

Put BuiltWith to work from one prompt

Connect hyreflow to Claude or ChatGPT and ask for the outcome. It reads the playbook above before it makes a single call.