Skip to content
ClickRuntime

Automate Hugging Face

Follow the Hugging Face Hub without refreshing it. Get the day's most upvoted papers, a weekly shortlist of trending models for your task, and a message when a model repo you depend on gets a new commit. Explain it to your AI assistant, check what it will do, and it keeps checking the Hub for you.

Add to ChatGPTAdd to Claude
Works inChatGPTClaudeClaude CodeCursorCodexVS CodeGemini CLIZedopencodeAny MCP client

Try asking

Create a ClickRuntime automation: every morning at 7:30, get today's Hugging Face daily papers with more than 20 upvotes and email me each title, link and a one-sentence summary.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Ideas

What you can automate in Hugging Face

Research worth reading, models worth trying and repo changes worth knowing about, delivered to your inbox or Slack. These are ready-made starting points. Anything else you can describe works too.
DailyAI

Get the top new AI papers each morning

Each morning you get the most upvoted papers from Hugging Face's daily list, each with a link and a one-line summary.

See how it works
Weekly

Get a weekly shortlist of trending models

Every week you get the top trending models in your task area, leaving out ones you've already been sent.

See how it works
Every 6h

Know when a model you use is updated

When a model or dataset repo you rely on gets a new commit, you hear about it in Slack within hours.

See how it works Your own logic

Any other automation you can describe in words

Your own rules, schedule and AI steps with Hugging Face, plus any other app. Describe it and your assistant builds it.

See how to build your own

Build your own

Build any Hugging Face automation you can describe

The ideas above are ready-made starting points, not a fixed list. Describe what Hugging Face should do in your own words, with your conditions, other apps or an AI step, and your assistant writes it, tests it and runs it on ClickRuntime.

  • Your own rules

    Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.

  • Any number of apps

    One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.

  • AI where it helps

    Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.

  • On a schedule or on each event

    Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

For example, ask your assistant

Every hour, run new product reviews through a Hugging Face sentiment model and alert me if the share of negative reviews goes above 20 percent.

For each new row in my Google Sheet, use a Hugging Face model to translate the text into Spanish.

When a new Zendesk ticket arrives, classify it with a Hugging Face model, tag the ticket and log the result in Airtable.

Beyond chat

Have Hugging Face work when you're not in the chat

Connecting Hugging Face to ChatGPT or Claude lets you ask about it while you chat. ClickRuntime handles the part that should happen on its own: checks on a schedule and actions on each new event, set up from the same chat and running after you close it.

Setup

Connect Hugging Face

Hugging Face connects with a user access token from your account settings. A read-only or fine-grained token is enough for watching the Hub.

Hugging Face

AI / Model hub & inference

  1. On huggingface.co, open Settings, then Access Tokens.
  2. Create a new token. Fine-grained is recommended; give it read access to the repos you want to watch.
  3. Copy the token. It starts with hf_.
  4. In the ClickRuntime dashboard, open Connections & secrets and save the token as a secret for Hugging Face.

Good to know

Hugging Face limits that affect automations

  • Team and Enterprise organisations can require an admin to approve fine-grained tokens, or reject read and write tokens with a 403 error. Check with your org admin if calls are refused.
  • Gated models only work after you accept their terms on the Hugging Face website with the same account.
  • The same token also works with Hugging Face Inference Providers, so you don't need a second credential to run hosted models.

FAQ

Questions about automating Hugging Face

What can ClickRuntime see on Hugging Face?
Whatever your token allows: public models, datasets and papers, plus private or gated repos if the token has access. A read-only token can't change anything on the Hub.
Why am I getting a 403 error?
Your organisation may block read and write tokens or need an admin to approve fine-grained ones. A gated model also returns errors until you accept its terms on the website.
How quickly will I hear about a new commit?
On the schedule you choose, such as every 6 hours. The automation compares each repo with what it saw last time and only messages you when something changed.
Does the papers digest need AI?
Only for the one-line summaries. That uses the AI included with every ClickRuntime plan, so you don't need your own AI key. Without summaries you still get titles and links.
Is this a Hugging Face connector for ChatGPT or Claude?
Not for chatting with Hugging Face data. A chat connector lets your assistant read and change Hugging Face while you're in the conversation. ClickRuntime is for the work that should happen without you: you set up an automation from the chat once, and it keeps running on a schedule or on each Hugging Face event.

Related pages

Keep exploring

Tell your assistant what Hugging Face should do

Free plan. No credit card.

Add to ChatGPTAdd to Claude