Firecrawl and Hugging Face Integration

Demonstration of how apps are integrated in WEXTL workflow builder[4]

Keep Firecrawl and Hugging Face matched by integrating their events and actions. When ai events happen in Firecrawl, update the Hugging Face automatically - without any line of code in visual workflow builder.

  • 3-day trial
  • Cancel anytime
  • Up to 10 minutes quick set up
  • GDPR
  • Data Encryption
  • 2FA
  • Local Data Region

Learn about Firecrawl and Hugging Face

Detailed info you need to know about Firecrawl and Hugging Face integrations in WEXTL. Explore which modules apps support and how you connect them.

  • Firecrawl

    • AI
    • 30 searches
    • 25 actions

    Scrape and crawl websites, extract structured data, search the web, and manage Firecrawl monitors and team usage.[5]

  • Hugging Face

    • AI
    • 1 trigger
    • 72 searches
    • 77 actions

    Search and manage models, datasets, Spaces and collections, run chat completions and react to Hub events.[6]

How to connect Firecrawl to Hugging Face

Set up your Firecrawl and Hugging Face integration in 3 simple steps[2]. No coding required. Up to 10 minutes setup.

How does the integration between Firecrawl and Hugging Face work in WEXTL?

WEXTL exposes actions and triggers for Firecrawl and Hugging Face that help you connect apps and automate repetitive tasks[1]. A trigger is an event that happens, and an action is a step that performs when the event has occurred.

Hugging Face triggersFirecrawl actions

Hugging Face modules

  • Watch Events Starts the workflow the moment Hugging Face calls the webhook, with the Event, Repo and Webhook of each call.
  • Add a Collection Item Puts a paper, Space, dataset, model or another collection into a collection of yours. Add a Note to leave a comment on the entry.
  • Add a Discussion Comment Posts a Comment into a discussion thread and shows the New Message that was created.
  • Add a Paper Comment Posts a Comment under a paper on the Hub, using its Paper ID. The result shows the New Message.
  • Batch Update Collection Items Edits several items of one collection in a single call, each row naming its own Item ID. Saves running an item update once per row.
  • Cancel a Job Stops a running job in your account or in an organization you belong to. The result shows the job Docker Image and Environment.
  • Compare Revisions Diffs two revisions of a repository, entered as Compare. Turn on Raw Diff to get the plain diff text.
  • Count Jobs Totals the jobs of a user or organization. Use Stage to count only the jobs in one stage, such as COMPLETED or ERROR.
  • Create a Branch Opens a new line of work in a repository. Use Starting Point to branch off a chosen commit, or turn on Empty Branch to start with no history.
  • Create a Bucket Creates a storage bucket on the Hub in a chosen Region with a set Visibility. Add a Description to document what it holds. The result shows the URL, Name and ID.
  • Create a Chat Completion Sends Messages to a Model on Inference Providers and returns the Answer with its Usage. Provider costs apply.
  • Create a Collection Starts a collection owned by you or an organization. Seed it with a First Item Type and First Item ID, or turn on Private to hide it.
  • Create a Commit Adds, changes or deletes files in one commit, using Files and Files to Delete. Turn on Open a Pull Request to send the change for review. The result includes the Commit Oid and Commit URL.
  • Create a Container Creates a container repository on the Hub, with a Region, Visibility and Description. The result shows the URL, Name and ID.
  • Create a Discussion Opens a discussion for a repository, or a pull request when Pull Request is turned on. The result shows the Num and URL.
  • Create a Repository Creates a repository of your chosen Type. Use Visibility for public, private or protected, Organization to create it under a team, and SDK for a Space.
  • Create a Scheduled Job Runs a container on a cron Schedule on the chosen Hardware, from a Docker Image or a Space. Set Environment and Secrets for the run. Billed when it runs.
  • Create a Tag Tags a revision of a repository with a Tag name. Add a Message to annotate it, or set Revision to tag something other than main.
  • Create a Trusted Publisher Trusts an OIDC issuer to access a repository, based on the Issuer URL and the Claims it presents. Use Permissions to allow only reading or only writing content.
  • Create a Webhook Calls your URL when chosen Events fire on the accounts and repositories listed under Watched. Add a Secret to sign each call.
  • Create or Update a Space Secret Saves a secret under a Key for a Space, creating it or overwriting it. Add a Description to note what it is for.
  • Create or Update a Space Variable Saves a variable under a Key on a Space, creating it or overwriting its Value. Use Description to document it.
  • Delete a Branch Deletes a branch from a model, dataset or Space repository on the Hub.
  • Delete a Bucket Removes a bucket you own, either in your account or in an organization.
  • Delete a Collection Deletes a collection of Hub items from your account.
  • Delete a Container Removes a container repository from the Hub.
  • Delete a Container Tag Removes a version Tag from a container repository.
  • Delete a Discussion Removes a discussion thread from a repository.
  • Delete a Pull Request Ref Deletes the git ref behind a pull request.
  • Delete a Repository Deletes a repository. Add an Organization when it lives under one, and set Type to choose between model, dataset and Space.
  • Delete a Scheduled Job Deletes a cron job from your account or from an organization you belong to.
  • Delete a Space Secret Deletes the secret saved under a Key in a Space.
  • Delete a Space Variable Removes the variable stored under a Key within a Space.
  • Delete a Tag Removes a repository tag. Use Revision to name it.
  • Delete a Trusted Publisher Removes an OIDC issuer from the trusted list of a repository.
  • Delete a Webhook Deletes a webhook from your account, which ends its calls to the URL.
  • Delete Notifications Clears notifications of the connected account, narrowed by Discussion Ids, Read Status, Repo Type or Repository Name.
  • Delete Space Volumes Unmounts and removes all storage volumes mounted on a Space.
  • Download a File Fetches a file from a repository by its Path, at the main branch or at a Revision. Returns the File with its File Name, Size (Bytes) and Content Type.
  • Duplicate a Job Starts a new job with the same settings as an existing one, using its Job ID.
  • Duplicate a Repository Copies a Space to New Repository, hardware included. Adjust the copy with Hardware and Sleep Time (Seconds), then follow progress with Get Duplication Status.
  • Get a Bucket Reads one storage bucket, giving its Author, Private flag, Description and Created At.
  • Get a Collection Loads one collection with its Title, Owner and Position.
  • Get a Container Reads one container repository, giving its Author, Private flag and Updated At.
  • Get a Dataset Loads a dataset repository, showing its Likes, Downloads and Tags.
  • Get a Discussion Reads a discussion or pull request by its Num.
  • Get a Folder Size Totals the bytes under a Path inside a repository, at the main branch or a chosen Revision.
  • Get a Job Looks up a job by its Job ID and shows its Created At, Docker Image, Timeout and Command.
  • Get a Model Fetches a model repository, giving its Likes, Downloads, Commit and Tags.
  • Get a Model Revision Reads a model as it was at a given branch, tag or commit. Use Revision to choose which, and turn on Include File Sizes to add each file size.

Firecrawl modules

  • Ask Support Agent Sends a Question to the Firecrawl support agent. The reply has the Answer, a Confidence value, Fix Parameters and a Validation result.
  • Batch Scrape URLs Starts a scrape of many URLs at once and returns a batch job ID. Use Formats to set the output formats for every URL. Rejected URLs are listed under Invalid URLs.
  • Cancel a Batch Scrape Cancels a batch scrape job. Output includes its Status.
  • Cancel a Crawl Job Stops a crawl job from running further and reports its Status.
  • Cancel an Agent Job Cancels an agent job and returns Success.
  • Crawl Website Begins a crawl of a website from its URL and produces a crawl job ID. Use Crawl options to add extra crawl settings such as limit or includePaths.
  • Create a Monitor Creates a monitor from a Name, a Schedule and 1 to 50 Targets. Use Additional options to attach a webhook or an email notification.
  • Create an Interact Session Opens an interact session and returns its ID, Cdp URL, Live View URL and Expires At. Use Session options to pass vendor session settings.
  • Delete a Monitor Removes a monitor from your Firecrawl team.
  • Delete an Interact Session Deletes an interact session. Output includes the Session Duration Ms and Credits Billed.
  • Execute a Browser Interaction Runs your Code inside an interact session. The run reports its Stdout, Result, Stderr and Exit Code.
  • Extract Structured Data Starts an extract job that pulls structured data from URLs, guided by a Prompt and a Schema. Follow it with Get Extract Status to read the data.
  • Find Similar Papers Finds research papers related to a seed paper, ranked by Intent. Use Mode to set the structural expansion, turn on Rerank to re-rank the candidates, and set Limit for up to 500 results.
  • Get a Monitor Reads one monitor. Output includes its details as Data.
  • Get a Monitor Check Opens a single check from a monitor. Output includes Data for that check.
  • Get a Threat Protection Policy Retrieves the threat protection policy set for your team. Output includes it as Data.
  • Get Agent Status Checks an agent task started with Start an Agent Task and, once it finishes, returns its output. Output includes the Model, Effort and Credits Used.
  • Get an Agent Snapshot Returns one snapshot taken during an agent job. Snapshot IDs appear in the artifact.updated events of Get an Agent Trace.
  • Get an Agent Trace Shows the trace of an agent job, with its Events, Credits Used and Active Browser Sessions.
  • Get Batch Scrape Errors Lists the Errors from a batch scrape job, along with the URLs listed under Robots Blocked.
  • Get Batch Scrape Status Checks a batch scrape begun with Batch Scrape URLs. Output includes its Status, Total, Completed count and the scraped Data.
  • Get Crawl Errors Fetches the Errors of a crawl job, plus the URLs that Robots Blocked.
  • Get Crawl Status Follows a crawl started through Crawl Website and shows how many pages are Completed out of the Total. Output also includes the crawl Status and the scraped Data.
  • Get Credit Usage Shows how many credits your Firecrawl team has used. Output includes Data with the usage figures.
  • Get Extract Status Checks an extract job begun with Extract Structured Data and returns its Status. Once it finishes, output includes the extracted Data and Tokens Used.
  • Get Historical Credit Usage Retrieves credit usage for your team grouped by Periods. Turn on By API key to break the figures down by API key instead of the team total.
  • Get Historical Token Usage Finds token usage over past Periods. Use By API key to see each API key separately in place of the team total.
  • Get Paper Details Fetches one research paper by its Paper ID, along with the Query and its Passages.
  • Get Queue Status Gets your team job queue: Jobs In Queue, Active Jobs In Queue, Waiting Jobs In Queue and Max Concurrency.
  • Get Scrape Status Re-fetches the stored result of a scrape that already finished, using its Scrape job ID. Scrape URL returns the full result straight away, so this is for reading it again later.
  • Get Token Usage Returns token usage for the Firecrawl team. Output includes the totals as Data.
  • Interact with a Scrape Session Sends Actions to the interactive session of a scrape, using the Scrape job ID of that scrape. The run reports Stdout, Result and Live View URL.
  • List Active Crawls Shows the crawls that are active on your account, each with its ID, Team ID, URL and Options. Use Limit to cap how many are returned.
  • List Agent Runs Retrieves agent runs with their Status, Origin and Created At. Use Before to list runs created before a time.
  • List Interact Sessions Finds interact sessions with their Status, Cdp URL and Live View URL. Use Status to keep only sessions in one status.
  • List Monitor Checks Reads past checks of a monitor, each with its Trigger. Use Status to filter by status and Limit to cap results across pages.
  • List Monitors Lists monitors with their Name, Status, Schedule and Next Run At. Use Limit to cap the total fetched across pages.
  • List Team Activity Gets team activity entries, each with an Endpoint, API Version, Created At and Target. Use Endpoint to keep activity for one endpoint.
  • Make an API Call Runs a free-form request against the Firecrawl REST API using your saved credential.
  • Map Website URLs Maps a site starting from its URL and returns the Links it finds. Use Map options to add extra settings such as search or sitemap.
  • Parse a File Parses an uploaded File and returns the extracted Data, along with a Success flag.
  • Preview Crawl Parameters Returns Data with the crawl parameters Firecrawl would use for a URL and a natural-language Prompt.
  • Run a Monitor Triggers a run of an existing monitor on demand and returns an ID and Data.
  • Scrape URL Scrapes one URL and returns the result straight away, with no job to poll. Use Formats to set output formats and Scrape options for more vendor settings.
  • Search Developer Index Looks up a Query in the developer index and returns ranked results with ID, Type, URL, Title and Passages. Use Types to narrow the kinds of result and Limit to cap them at up to 100.
  • Search Developer Index (POST) Runs the developer index search on your Query, sent as a body request. Narrow the results with Types and set how many to keep with Limit.
  • Search Firecrawl Docs Answers a documentation Question from the Firecrawl docs. Output includes the Answer, Evidence and Usage.
  • Search Research Papers Finds research papers for a Query, ranked, with Title, Abstract and Score on each. Narrow them with Authors, Categories, From and To, and set Limit up to 500.
  • Search Web Runs a web search for a Query. Use Limit to set how many results are returned and Search options for extra vendor settings. Output includes Data and Credits Used.
  • Start an Agent Task Begins an agent task from a Prompt and issues a job ID. Read the output later with Get Agent Status. Use Agent options for extra vendor fields.

Explore alternative integrations

There are other apps[9] supported by WEXTL that can be paired with Firecrawl and Hugging Face integrations. Pick any from the list below if the current combination isn't the one you need.

Automate Firecrawl and Hugging Face on WEXTL®

Claim your 3-day trial to build Firecrawl with Hugging Face integration and access every WEXTL® feature.

Cancel anytime.

Frequently asked questions

Common questions about connecting Firecrawl and Hugging Face.

How do I connect Firecrawl and Hugging Face?

Connect your Firecrawl and Hugging Face accounts once, pick a trigger in one app and an action in the other, then map the fields so data flows automatically between them.[3]

What can I automate between Firecrawl and Hugging Face?

Example: when the "Watch Events" trigger in Hugging Face fires, WEXTL can "Ask Support Agent" in Firecrawl. Firecrawl has 55 actions (including Ask Support Agent, Batch Scrape URLs, and Cancel a Batch Scrape). Hugging Face has 149 actions (including Add a Collection Item, Add a Discussion Comment, and Add a Paper Comment). Add filters and transforms between steps when you need them.[1]

Can Firecrawl trigger actions in Hugging Face, and Hugging Face in Firecrawl?

Yes. The integration works in both directions. Use the triggers of each app to start a workflow and the actions of the other app to update it.[2]

Do I need to write code to integrate Firecrawl and Hugging Face?

No. Firecrawl-to-Hugging Face automations are built visually on the canvas. You can optionally add custom JavaScript with Functions when you need advanced logic.[4]

Does Firecrawl integrate with Hugging Face in real time?

Yes. Trigger-based automations start the moment Firecrawl (or Hugging Face) fires a new event. Webhook-backed apps run within seconds, and polling-only apps re-check on a schedule you control.[7]

How long does it take to set up a Firecrawl + Hugging Face integration?

A first automation typically takes 5–10 minutes: connect the credential of each app once, drop a trigger + action onto the canvas, map the fields, and turn the workflow on.

Do I need a paid plan to connect Firecrawl with Hugging Face?

You can build your Firecrawl + Hugging Face automation on a 3-day trial with every feature unlocked. Cancel anytime.[8]

References

List of sources used to gather information about the Firecrawl and Hugging Face integration.

  1. Firecrawl and Hugging Face integration source code, module specs and credentials implementation.
  2. Our Firecrawl and Hugging Face integration documentation, structured input and output parameters, scopes, and authentication methods.
  3. Official vendor API documentation for Firecrawl and Hugging Face, used to verify field meanings, authentication flows, and anything our own specs don't fully capture.
  4. WEXTL® visual workflow builder, anonymized data from our technical support team.
  5. Firecrawl integration information
  6. Hugging Face integration information
  7. WEXTL® Scheduling
  8. WEXTL® Pricing and Trial
  9. WEXTL® Apps Library

How we write our apps documentation

Explore how WEXTL® crafted Firecrawl and Hugging Face integration page documentation. Used sources, the role of AI, and how the team validates the result.

Explore Firecrawl and Hugging Face, or get started