Daily
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.
- Runs
- Daily
- Apps
- Hugging Face
- AI
- Yes, uses the built-in AI allowance
- Access
- read (public data)
Send this to your assistant
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.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
Hugging Face's daily papers page surfaces the research people in the community are actually reading, but it is one more tab to open and it moves quickly. A researcher or ML lead who checks it irregularly misses the paper everyone discussed on Tuesday, then hears about it in a meeting on Friday and has to catch up on the abstract while others are already comparing it to their own approach.
Each day, ClickRuntime fetches the daily papers list, keeps only those with enough upvotes to be worth your time, and emails you the result. If you want, built-in AI adds a one-line plain-English summary under each title, so you can decide in seconds which abstracts deserve reading.
It works well for small research groups, ML engineers keeping a pulse on a field, and anyone who wants the signal without the browsing.
What you get out of it
Stay current without browsing
A short email in your inbox replaces a daily visit to a feed. You see what is getting traction while it is new, which matters in fields where a method can be outdated within a month.
Upvote filter keeps the noise out
Only papers past a threshold are included, so a quiet day gives you a short list and a busy day gives you the standouts. You are not scrolling through dozens of entries to find three worth reading.
One-liners speed up triage
A sentence explaining what each paper claims lets you skip the ones outside your area and open the relevant ones. Deciding takes seconds rather than opening ten abstracts in separate tabs.
Shared awareness in a team
Forward the email, or point it at a team address, and everyone discusses the same papers. Journal clubs and stand-ups get a ready list instead of each person bringing their own scattered finds.
Less fear of missing the key paper
Falling behind on literature is a quiet worry for practitioners. A reliable daily summary lowers it, because a significant paper will appear in front of you within a day of gaining attention.
How it works
What happens, step by step
Every morning, ClickRuntime fetches Hugging Face's daily papers list.
It keeps only papers with more than 20 upvotes.
AI reads each abstract and sums it up in one sentence.
You get one email listing each paper with its title, upvotes, link and one-line summary.
Before it runs live
- Connect Hugging Face
What you get
Build your own
Need it to work differently?
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
- Change what the AI looks for, or how it writes the result
- 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
from clickruntime import on_trigger, notify, http, ai
MIN_UPVOTES = 20
@on_trigger
def run(event):
papers = [p["paper"] for p in http.get("https://huggingface.co/api/daily_papers").json()
if p["paper"].get("upvotes", 0) > MIN_UPVOTES]
if not papers:
return {"papers": 0}
lines = []
for p in papers:
one_liner = ai.generate(f"Summarise this abstract in one sentence:\n{p['summary']}", max_output_tokens=80).text
lines.append(f"{p['title']} ({p['upvotes']} upvotes)\nhttps://huggingface.co/papers/{p['id']}\n{one_liner.strip()}")
notify.email_me(f"Hugging Face daily papers: {len(papers)}", "\n\n".join(lines))
return {"papers": len(papers)}FAQ
Common questions
How do I set the upvote threshold?
Are the AI summaries based on the full paper?
Can I get it only for certain topics, like speech or vision?
What permissions does it need?
Does it need AI?
How many runs does it use?
Can I change how it works?
Related
You might also like
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 worksKnow 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 worksGet a daily news digest in Slack
Each morning your team gets a short summary of what's new on the sites and blogs you follow.
See how it worksKeep exploring
Set up “Get the top new AI papers each morning” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.