Search for your whole company

Excellent search over everything your company knows.

Connect the places your knowledge lives, decide who can search what, and get answers that show their sources. Put it on your website, inside your product, in front of your support team, and behind the AI agents you are building.

Connect websites and files today. Confluence, GitHub, Notion and more next.

Ask· collection: customer-support · website + files
How do refunds work for annual plans?

Sources

Bring your knowledge from wherever it lives.

Websites, files, wikis, help desks, code. Hayfork reads each one, keeps the structure that matters, and drops the clutter. Once connected, a wiki page, a web page and a PDF are searched exactly the same way.

Website crawler

Now

Any public site: documentation, help center, blog, changelog. Hayfork reads the content, skips the menus and footers, and keeps pages fresh when you re-sync. Sites built for AI readers index even faster.

File uploads

Now

PDF, Word, Markdown and text. Drop in a folder of policies, contracts or handbooks. Originals are kept safely and re-read automatically when we improve how content is understood.

Every connection asks for the least access the source allows, such as one Confluence space or one repository. Credentials are stored encrypted, never shown again, and can be revoked from the console at any time.

Collections

Decide who can search what.

Group sources into collections, and point each search box, product feature or agent at the collection it should see. The same help center can serve your public website and your internal support team; connect it once and use it in both.

Sources

docs.acme.devwebsite · 1,240 pages
help.acme.devwebsite · 380 pages
Runbooksconfluence space · next
Contracts 2026uploads · 42 files

Collections

Public supportdocs + help
On-call agentdocs + runbooks
Legal reviewcontracts only

Consumers

Search boxon your website
Inside your productthrough the API
Your AI agentsone key per agent

Your workspace is yours alone. Nothing is shared between customers, and every key you hand out does one job: a search key can only search, so the key on your public website can never add, change or delete anything.

Build with it

Great answers for people. Reliable answers for agents.

The same knowledge powers a search box your customers love, answers inside your own product, and the agents your team is building. Add Hayfork to your company's agent tooling once and every agent gets trustworthy answers from exactly the collections you allow.

UISearch your customers love Now

Understands the question, not just the keywords. Finds the right page whether someone types an exact error code or describes a problem in their own words, and shows where in the document the answer sits.

POST /search
{ "collection_id": "public-support",
  "query": "rate limit error 429" }

APIAnswers inside your product Now

Ask a question, get back the exact passages that answer it, numbered and linked to their source, sized to fit whatever is asking. Perfect for in-app help, support tooling and assistants.

POST /retrieve
{ "collection_id": "on-call-agent",
  "query": "payments queue backlog",
  "top_k": 8, "max_tokens": 4000 }

MCPReady for your agents Next

Plug Hayfork into the agent tools your company already uses, so Claude, Cursor and your own agents answer from your knowledge instead of guessing. Ready-made integrations for popular agent frameworks ship today; the MCP connector is next.

# python, today
client.retrieve_context(
  "on-call-agent", "payments queue backlog",
  top_k=6, max_tokens=3000)

Use cases

One platform, many ways to use it.

Starting points our customers pick most often. Each one is just a few sources, a collection, and somewhere to put the search.

Docs and support search

Docs, help center, changelog and blog searched together. Your customers stop opening five tabs to find one answer, and your support team stops answering questions the docs already cover.

websitessearch boxin-app answers

Grounding for internal agents

An on-call assistant that knows your runbooks, a sales assistant that knows your pricing and security answers. Each one sees only the collection you give it, and cites what it used.

confluence · nextfilesagents

Search inside your product

Help, knowledge base and content search inside your own interface, with results that feel native to your product.

any sourcesAPIsearch key

Agencies and consultancies

A workspace for each client, their sources connected, a key handed over. One platform behind every assistant you build for them.

workspacesscoped keysself-hosted

How it works

Connect it, and it just answers.

Four steps happen behind the scenes. You only do the first one.

1

Connect

Paste a website address, drop in files, or connect a wiki. Re-sync whenever you like; nothing gets duplicated.

2

Clean up

Menus, footers and clutter are removed. Headings and structure are kept, so every answer knows which section of which document it came from.

3

Understand

Content is understood by meaning as well as by exact words, so a precise error code and a vague description both find the right page.

4

Answer

People get clean results with highlights. Agents get the exact passages with sources. Both only ever see the collections they are allowed to.

Where it runs

Your data stays yours.

Use Hayfork hosted by us, or run the whole thing inside your own network. Either way, your content is understood by a model we run next to your data, not sent to a third-party AI provider unless you choose to.

How content is understood

  • Built-in model, running on our servers or yours. No extra accounts, no per-word charges.
  • Multilingual option for content in several languages.
  • Google or OpenAI models if you prefer them; switch with one setting.
  • Switching is safe: nothing already indexed gets mixed up or lost.

Access you control

Your workspace is separate from everyone else's. Keys are shown once, can expire, and can be revoked instantly.

searchCan only search. Safe on a public website or in an agent's hands.
ingestCan add and update content. For your own systems.
adminEverything, including creating and revoking keys.

Pricing

Simple pricing. Documents and searches, nothing else.

Start free with your own sources. Upgrade when your collections or your agents need more.

Free
$0 / month
  • 2 sources, 300 documents
  • 1,000 queries / month
  • Search box and playground
  • 1 search key
Start free
Business
$299 / month
  • Unlimited sources, 25,000 documents
  • 500,000 queries / month
  • Users and roles, audit log
  • Priority support
Talk to us
Self-hosted
Yours / your cloud
  • Same product, your infrastructure
  • Built-in language model included, no external AI provider
  • Unlimited documents and queries
  • Annual licence with support
Talk to us

A document is a page, file or record, counted once however many collections include it. Re-syncs are free. Searches from people and agents count the same.

Questions

The ones we get asked first.

Does my website need anything special to be indexed?

No. Paste the address and Hayfork reads it, keeping the content and dropping menus, footers and widgets. Sites that publish AI-friendly versions of their pages index a little faster, but any site works.

How is this different from the search built into my docs or wiki?

Built-in search covers one property and lives only there. Hayfork indexes many sources into collections you define and serves them anywhere: your website, your product, your support desk, and the agents your team runs.

What does an agent actually get?

The exact passages that answer its question, numbered and linked to their source documents, sized to fit the agent's limits. Integrations for popular agent frameworks are available today, and an MCP connector for company-wide agent tooling is next.

How are connections to Confluence and other tools secured?

Each connection asks only for what it needs, for example one Confluence space or one repository. Credentials are stored encrypted, never shown again, and can be revoked from the console at any time, taking effect immediately.

Does my content leave my infrastructure?

On hosted plans it lives in your own separate workspace on our servers and is never sent to a third-party AI provider unless you choose one. On the self-hosted licence nothing leaves your network.

How good is the search, honestly?

Good enough that we publish the numbers. The console has a Benchmarks page with measured results on a public dataset, and you can build your own benchmark from real questions your customers ask and see the score change as you tune it.

Connect one source today. Add the rest as you go.

Free plan, no card. Start with a website or a folder of files, and have excellent search on it before your coffee is cold.

Start free