Search for your whole company
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.
Sources
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.
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.
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.
Connect a single space with access limited to that space. Keep it in sync, and give a team or an agent exactly the pages it should see and nothing else.
READMEs, issues and discussions from the repositories you choose.
Selected pages and databases, kept in sync.
Zendesk, Intercom and Freshdesk articles, plus resolved tickets you choose to include.
Google Drive folders and S3 buckets, by prefix.
Records from your own systems, turned into searchable documents with a query you control.
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
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.
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
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.
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" }
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 }
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
Starting points our customers pick most often. Each one is just a few sources, a collection, and somewhere to put the 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.
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.
Help, knowledge base and content search inside your own interface, with results that feel native to your product.
A workspace for each client, their sources connected, a key handed over. One platform behind every assistant you build for them.
How it works
Four steps happen behind the scenes. You only do the first one.
Paste a website address, drop in files, or connect a wiki. Re-sync whenever you like; nothing gets duplicated.
Menus, footers and clutter are removed. Headings and structure are kept, so every answer knows which section of which document it came from.
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.
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
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.
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
Start free with your own sources. Upgrade when your collections or your agents need more.
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
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.
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.
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.
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.
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.
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.
Free plan, no card. Start with a website or a folder of files, and have excellent search on it before your coffee is cold.