What is the 10K App Store Indexor?

A natural-language lookup tool over the US App Store charts from soloiaros: describe an app, a look, or a feature — “yellow bird icon”, “habit tracker with streaks” — and get matching titles with a likelihood beside each one.

Discovery never sends the whole catalog to a model: a local shortlist of at most 120 apps goes to Jev once as a single jev-latest request via OpenRouter, and apps it scores below 30% stay off the results entirely.

How do I set up the index?

You build the catalog yourself: the committed tree has no data/catalog.sqlite, and the README points at Apple's public chart and Lookup feeds so you can expand the seed, change the country, or add titles on demand. The digest truncates before the exact setup commands.

What do the percentages and provenance tiers mean?

Every shown field is verified, estimated, or unavailable; downloads and MAU stay empty unless a cited source or recorded method is attached. Discovery results carry the Jev score beside each app, and anything under 30% is hidden.

What kinds of queries can I ask?

Three shapes: factual (a short name or a “what” question gets an app's stored fields with no language model), comparative (sorted by stored momentum once two daily rating snapshots exist), and discovery (anything else, answered by Jev-scored matches).

Does it replace third-party analytics tools?

No: it is a local index over public chart and Lookup feeds, not a paid analytics dump. The README says US store spend per day is estimated from top-grossing ranks with a named method, us-grossing-power-v1, and everything that cannot be justified stays unavailable.

Who built it and how new is it?

soloiaros's MIT-licensed TypeScript repo, created 2026-09-23 and last pushed 2026-10-04, with 61 stars and 5 forks. It retargets the aayans-yc-indexor interaction shape (MIT) at Apple's public feeds.

Jev directory

CommunityJev Tools & CLIs

10K App Store Indexor

Natural-language lookup over the US App Store top charts: describe an ambiguous feature, a look, or a name and get matching apps with how likely each one is, scored by a single Jev request over a local shortlist.

See highlights Open github.com

Stars: 61
Language: TypeScript
License: MIT
Reading time: 3 min
Published by: Community
Author: soloiaros
Last verified: Oct 2026

soloiaros/archies-appstore-lookup

User repository on GitHub

View on GitHub

Natural language Jev-powered AppStore indexing tool: describe an ambiguous feature of an app, get and research matching apps from the US top-charts. Ideal for solo developers doing market research.

Forks: 5
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

Tagscommunity github appstore embeddings research

Works forJev for Ranking Jev for Verification

Used inJev for Software & DevTools

Languages: TypeScript
Platforms: Next.js Cloudflare OpenRouter SQLite
Capabilities: Open sourceRequires API key

Highlights

README: ask in plain English — “a minimalist habit tracker” or “green owl icon” — and get matching App Store titles with a likelihood beside each.
Shortlisting merges BGE text embeddings, SigLIP2 icon embeddings, name, tag, and word matches into a local list of at most 120 apps that goes to Jev once.
Apps Jev scores below 30% stay off the results; every field is marked verified, estimated, or unavailable, and downloads or MAU stay empty unless cited.
The committed tree ships no data/catalog.sqlite — you build the index from Apple's public chart and Lookup feeds, and the site is a plain Node/Next.js app.
MIT, 61 stars, 5 forks, TypeScript, created 2026-09-23, last pushed 2026-10-04; query shapes are factual, comparative, and discovery.

Watch out

README reviewed 2026-10-17 and truncated at the end of the discovery path, so install steps, pricing, and accuracy numbers are not in the digest. Discovery sends one shortlist per query to Jev (jev-latest via OpenRouter); comparative momentum stays unavailable until two daily rating snapshots exist, and US store spend per day is only an estimate under a named method. The interaction shape is adapted from aayans-yc-indexor (MIT), and the tree does not ship that project's Core ML binary.

Questions about this entry

Short answers drawn from the linked project or page.

From the Jev guides

Original write-ups on what this entry is for.

Jev at home: voice pipelines, Assist routing, and sentinels

Oct 16, 2026

How Home Assistant conversation agents, macOS voice pipelines, and an advisory sentinel put a fast typed decision in the loop — one call per utterance, thresholds in code, and a daily token budget.

Jev Tools & CLIs#home-assistant#voice#automation

Read article

Search visibility, audited by decisions

Oct 16, 2026

Jev-based SEO tools split the crawl from the call: deterministic crawlers count and parse, while typed judgments rank fixes, place internal links, score search results, and track AI-answer mentions — with costs and caveats attached.

Jev Tools & CLIs#seo#search-visibility#audits

Read article

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai

10K App Store Indexor

Highlights

Questions about this entry

What is the 10K App Store Indexor?

How does it use Jev?

How do I set up the index?

What do the percentages and provenance tiers mean?

What kinds of queries can I ask?

Does it replace third-party analytics tools?

Who built it and how new is it?

Related terms

More Jev resources like this

From the Jev guides

From the Jev AI model community