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.

Runs: Weekly
Apps: Hugging Face
AI: Not needed
Access: read

Send this to your assistant

Create a ClickRuntime automation: every Monday at 9am, email me the 10 top trending text-generation models on Hugging Face that weren't in last week's email, with their likes and links.

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

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A developer building a speech feature wants to know when a strong new open model appears, but the Hugging Face model list changes constantly. Searching by task and sorting by trending takes ten minutes, so it only happens when there is a deadline, and by then a better model has been available for weeks. The team is still benchmarking last quarter's favorite while competitors have already moved on.

Once a week, ClickRuntime lists models in the task area you care about, sorted by what is trending or most liked, removes anything it has already sent you, and emails the new names. Each entry links to the model page so you can open the card straight away.

It helps product teams, ML engineers and technical founders who want to spot useful open models early without following social media.

What you get out of it

Find better models sooner
A model that moves up the trending list is usually getting real attention for a reason. Hearing about it the week it appears gives you a head start on testing it against what you use now.
Compare options before a build
Planning a feature around a model that is about to be replaced wastes engineering time. A regular view of what is rising helps you pick the base model that will still look sensible in a quarter.
No repeats clogging the list
Models already sent are dropped from later emails. Each digest is therefore new names only, so you do not reread the same top five every week and stop opening the message.
Scoped to your own task area
Filtering by a task such as text classification or automatic speech recognition means the email matches your work. Colleagues in other areas can have their own version with their own filter.
Cheap way to track a fast field
Open model releases are too frequent to follow manually. One weekly email gives a manageable habit that keeps a team informed, with no one assigned to watch the hub full time.

How it works

What happens, step by step

Once a week, ClickRuntime fetches the top trending text-generation models on Hugging Face.
It leaves out any model it sent you last week and keeps the top 10 of the rest.
You get an email listing each model with its likes and a link.

Before it runs live

Connect Hugging Face

What you get

RunsWeekly

Get a weekly shortlist of trending modelstoday, 9:00Succeeded

Email · Trending modelsacme-ai/Acme-7B-Instruct (1,284 likes) https://huggingface.co/acme-ai/Acme-7B-Instruct

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. 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.

Changes you can ask for

Run it at a different time, more or less often, or only on weekdays
Add an AI step, for example to summarize, sort or draft a reply
Add another app, for example also send it to Slack
Combine it with other Hugging Face steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.

trending_models_digest.pyexample

from clickruntime import on_trigger, notify, http, state

@on_trigger
def run(event):
    models = http.get("https://huggingface.co/api/models",
                      params={"filter": "text-generation", "sort": "trendingScore", "limit": 50}).json()
    last_week = set(state.get("last_week") or [])
    picks = [m for m in models if m["id"] not in last_week][:10]
    lines = [f"{m['id']} ({m.get('likes', 0)} likes)\nhttps://huggingface.co/{m['id']}" for m in picks]
    notify.email_me("Trending text-generation models", "\n\n".join(lines) or "No new trending models this week.")
    state.set("last_week", [m["id"] for m in picks])
    return {"models": len(picks)}

FAQ

Common questions

Can I limit it to a particular task, like text-generation?

Yes. Hugging Face models carry a pipeline task tag, and you can ask for one tag, such as text-generation or image-classification, or several. The list is then filtered to those tasks before sorting by trending or likes.

What does trending mean on Hugging Face?

Trending reflects recent activity, mainly likes and downloads over a short window, so a new model can outrank an older one with more total likes. If you prefer long-standing popularity, ask for sorting by likes or downloads instead.

Will the same model show up in more than one email?

No. The automation remembers the models it has already included and removes them from later digests. A model could reappear only if you reset that memory, so each weekly email lists names you have not yet been sent.

What permissions does it need?

read. Nothing else in your accounts is used.

Does it need AI?

No. It runs without AI, so it doesn't use your plan's AI allowance.

How many runs does it use?

One run each time it runs (weekly). Checks that find nothing to do and stop right away aren't counted.

Can I change how it works?

Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

DailyAI