Hidden ramen spots in Tokyo you must try
@tastingtokyo
AI Summary
Six under-the-radar ramen shops across Shinjuku and Shibuya, with the dish to order at each and how to actually find them.
#tokyo#food#travel
Food & TravelMar 12
Automations
Set the rules once.
Then stop filing.
If every recipe you save should land in one collection, say so once. Nemivo checks each new save against your rules and applies what you asked for, silently, on the way in.
Start Free 300 saves free · No credit card required
In short
An automation in Nemivo is a rule you write once: conditions on any of thirty fields, then up to twenty-five actions applied in order. Platform, creator, media type and date are on every plan; conditions on what the AI worked out, such as topic, intent or a detected entity, are Pro. Any rule can be dry-run against a real save before you turn it on.
When a save arrives
Platform is YouTubeTopic is programming
Move to Dev LearningTag #learning
Ran 214 times this month · last: 2 minutes ago
If this,
then that. Quietly.
A rule is a set of conditions and a set of actions. Both halves are yours, and neither of them runs until you have seen what it does.
- 01
Describe what to match
Conditions come from a catalog of thirty fields, grouped how you like: all of these and any of those, up to ten groups. Platform, creator, media type, date and a note being present are all plain fields; topic, intent and detected entities come from what the AI read.
- 02
Choose what happens
Move to a collection, add or remove one, add or remove a tag, favourite it, archive it, set a priority, append a note. Up to twenty-five actions on one rule, applied in order.
- 03
Test it before you trust it
A rule can be dry-run against a real item, draft included, before it is ever saved. You see which conditions matched and what would have been applied, without anything happening to your library.
- 04
It runs on every save after that
New saves are checked as they arrive, on their own background queue. Every execution is recorded as a success, a failure or a skip, so a rule that stops matching is something you can actually see.
The builder
Thirty fields, eleven actions.
Deliberately concrete: a rule you cannot predict is a rule you will turn off.
The plain fields
Platform, media type, collection, priority, favourite, archived, has-notes, title, description, creator name and handle, URL, content type, language, saved date.
The AI fields
Intent, subject type, content format, actionability, topic, category, summary text, tags, extracted entities, detected technologies, country, city, and the confidence score behind them.
Groups, and how they combine
Up to twenty-five conditions per group and ten groups per rule, so "all of these, or all of those" is expressible without a query language.
The eleven actions
Move to collection, add collection, remove collection, add tag, remove tag, mark or unmark favourite, archive or unarchive, set priority, append note.
A run history
Every application is logged with its outcome, so you can tell the difference between a rule that did nothing and a rule that quietly failed.
Rules you did not write
A collection suggestion you accept can be promoted straight into a rule, built from the traits that characterise that collection rather than from a guess.
The limits
Where the rules stop.
Automation that surprises you is worse than filing by hand, so these limits are on purpose.
One rule on the free plan
Free runs a single automation and Pro has no limit. Conditions on AI fields are Pro only, because they are what the enrichment step paid for.
They run on new saves
A rule applies to what arrives after it exists. Sweeping it back over everything you already have is not what this does; that is what filters and bulk actions in the library are for.
AI conditions wait for the AI
A rule matching on topic or intent can only fire once the save has been read. If credits have run out, the save still arrives, and the rule simply does not match yet.
It is not a workflow engine
No outbound webhooks, no third-party actions, no branching beyond the groups. Rules act on your library, and that is the whole surface.
The long version, including what is stored and where the AI sits, is on how it works.
The rules are only as smart as the reading.
Matching on "every recipe from a creator I follow" works because something already worked out that the save is a recipe. That is the enrichment step, running before any rule sees the item.
Pricing
Start free. Stay for the memory.
A real library on the free plan, forever. Not a trial: no countdown, no card, and no email on day seven asking for one. Pro removes the limits when your memory outgrows them.
Free
$0forever
A plan, not a trial. It does not expire.
- 20 AI credits a month
- 300 saved items
- 10 collections
- 1 automation
- 10 AI searches a day
- JSON export
No card. Ever.
Pro
Recommended$7.99/month
Built for people who save content every day.
- Unlimited AI organization
- Unlimited saved content
- Unlimited AI search
- Unlimited automations
Everything in Free, plus
- Faster AI processing
- AI insights in exports
- AI automation conditions
- Export as JSON, CSV, Markdown
- Public share links
- Bulk library reprocess
Cancel anytime
Free includes 100 welcome AI credits · Secure checkout by Polar
FAQ
Automations questions.
Move it into a collection, add or remove a collection, add or remove a tag, mark or unmark it as a favourite, archive or unarchive it, set its priority, or append a note. Nothing leaves Nemivo.
Want the mechanism and the limits in full? Read how it works.
Remember everything.
Forget nothing.
Nemivo reads the caption on everything you save, writes the summary, adds the tags and files it away. Months later you ask for it in your own words.
Start Free
A free plan, not a free trial · No credit card · Nothing expires
