CYBER MEDIA CYBER MEDIA Submit a tool
Language 中 EN

Explore

AI tools AI News

CYBER MEDIA

Services About Talk about a project

Work with us

Submit a tool Advertise

Account

Sign in

Home / Productivity · Writing · Agents / Winch

Winch

For indie developers doing ASO: uses your own coding agent to optimize store listings.

Visit Site
Category
Productivity · Writing · Agents
Price from official sources
Paid
Website
getwinch.app
Added to site
Nov 2, 2026

What is Winch

Winch is a macOS (13+) app for App Store and Google Play optimization driven by your own coding agent. It covers keyword rankings in 175 countries, localized copy, store screenshots and reviews. It has a 1-day free trial and a one-time price of $69 for the first 100 copies, $89 after that.

How to use

  1. Download Winch for macOS 13+ (Apple Silicon or Intel) and choose Start free trial: one day with everything, no key or card.
  2. Let Winch find the AI you already pay for: Claude Code, Codex, OpenCode, a local Ollama model or an OpenRouter key.
  3. Add your app and competitors by link or name;
  4. optionally connect App Store Connect or Play Console with your own keys.
  5. Ask the agent in plain words or use commands such as /competitors, /ideas, /optimize, /localize, /captions and /ship;
  6. turn on Act to watch it drive the app.
  7. Review scored listing options and store art, then confirm before anything is written to the store.
  8. Optionally drive it from Claude Code over MCP:claude mcp add winch -- /Applications/Winch.app/Contents/MacOS/Winch --mcp.

Use cases

  • Tracking App Store and Google Play keyword ranks in 175 countries Writing and scoring app names, subtitles and keywords, then localizing them into every language Captioning, translating and resizing screenshots for both stores Sorting new reviews into themes and catching regressions, with GitHub and Slack alerts Monitoring competitors' ranks and listing changes Planning a new app launch by checking names and winnable keywords

FAQ

Which AI do I need?

The one you already pay for. Claude Code with your Claude Pro or Max plan, Codex with your ChatGPT plan, OpenCode, a local Ollama model, or an OpenRouter key. Winch finds them on your Mac and runs them for you. It has no model of its own and sells no AI credits.

Do I need App Store Connect or Play Console?

No. Ranks, reach, difficulty, rivals, public listings and reviews all come from the stores' public pages. Connecting your account adds your own listings, reviews with replies, the store's numbers in Results, the Ship checklist and writing back.

What do reach and difficulty mean?

Reach is how many people a search reaches. Difficulty is how hard its top 10 is to beat.

Can I track competitors?

Yes. Add any app by its link or name, or let Winch suggest the ones that outrank you. You see its ranks next to yours, and every change it makes to its listing.

Does it work for Google Play?

Yes. Ranks, listings, store art, reviews and the store's own numbers all work for Google Play apps too, side by side with the App Store.

Is there a free trial?

Yes. Download Winch and choose Start free trial: a day with everything, once per Mac, no key or card needed. Enter a key any time to keep going.

Which Macs does it run on?

Any Mac with macOS 13 or later, Apple Silicon or Intel. Windows isn’t supported yet.

Price from official sources

Paid

  • One-time license:$69 once for the first 100 licenses, then $89.
  • A one-time license for the whole app, activated on your Macs with a key;
  • works offline.
  • Includes both stores and 175 countries, the agent and all 84 MCP tools on your own AI plan, optimization in every language, Studio and icon for both stores, and Reviews, Results, Activity and briefings.
  • Free trial:one day with everything, no key or card needed.

Check the official site for current pricing · Price not yet checked by our editors

Source: getwinch.app · Info as of Nov 2, 2026

Company

Name
Joydle Interactive LTD
Address
71-75 Shelton Street, London WC2H 9JQ

Log in Pricing page

Reviews

No reviews yet.

Alternatives

CorrectionReport an issue