¥150
App Store で開く
iPhone / iPad 対応
39.3MB
年齢4+
Small Todo - AI Task Breakdownはどんなアプリ？
Small Todo - AI Task Breakdownは、やりたくない用事を小さな工程へ分解して管理する仕事効率化アプリです。
やりたいことを入力すると、人工知能がそれをすぐに行える単位まで細かく分割します。例えば洗濯を済ませるという目標なら、かごを運ぶといった具体的な動作に置き換えてくれるため、着手への心理的な壁を低く保てます。処理を端末内で行う仕組みのため、電波のない場所でも動作し、独自のサーバーや自分の鍵と連携して動かすことも選べます。予定が変わったときも、内容を入力するだけで工程を自動で書き換えるため、常に最新の計画に沿って進められます。
手書き風の優しいデザインを採用しており、タスクを完了するたびに紙吹雪が舞う演出が見られます。やるべきことを一つずつ消していく過程を視覚的に喜びとして表現しているため、重い腰を上げて取り組みたい人に合っています。自分の好みや生活習慣を記憶させておけば、それらを考慮した工程の提案を受けられるため、個人の状況に寄り添った計画を立てられます。
アノアプリによる紹介文です。デベロッパー公式の説明はApp Storeでご確認いただけます。
Small Todo - AI Task Breakdownの注目ポイント
着手しにくい用事の細分化
重い腰が上がらない大きなタスクを、かごを運ぶといった具体的な動作まで分解します。一つひとつの工程を小さく定義するため、最初の一歩を踏み出す際の心理的な負担を減らせます。
電波のない場所での動作
処理を端末内で行うため、地下や山間部など通信環境が不安定な場所でも動作します。オンライン接続を待つストレスがなく、どこにいても自分のペースでタスクを進められます。
外部サーバーとの連携選択肢
自身のAPIキーや自宅のサーバーと連携する設定が選べます。プライバシーを重視する環境に合わせて、利用するモデルや接続先を自分の好みに合わせて使い分けることができます。
状況の変化に応じた自動更新
予定の変更をテキストで入力すると、残りの工程を自動で書き換えます。途中で状況が変わった際も、すべてをやり直す手間なく最新の計画に合わせてタスクを再構築できます。
価格履歴
現在は150円です。記録を始めた132日前から、価格は変わっていません。
アノアプリが独自に収集した価格履歴をもとに分析しています。
- 買い時判定
- 通常価格
- 記録期間
- 132日
- 最頻価格
- ¥150
- 記録上の最安値
- ¥150
価格更新履歴
| 日付 | 価格 |
|---|---|
| 2026-06-29 | ¥150 |
ランキング推移
ランキングデータがありません。
ランキング圏内（100位以内）に入ると記録が開始されます。
ユーザーレビュー （当サイト投稿）
まだレビューがありません。最初のレビューを書いてみましょう。
アプリ更新履歴 活発に更新中
Ver 1.19 2026-11-05
Local models
- If a list is deleted or finished while a local model is still answering, the model's memory is now freed, so switching models no longer keeps two in memory at once
- A local model you remove and add back straight away now works without restarting the app
- When two local models are in use at once, a message to one waits until the other finishes its answer
- If a list is deleted or finished while a local model is still answering, the model's memory is now freed, so switching models no longer keeps two in memory at once
- A local model you remove and add back straight away now works without restarting the app
- When two local models are in use at once, a message to one waits until the other finishes its answer
Ver 1.18 2026-11-05
Local models
- If the system needs memory and unloads a model while it is still loading, the app now says so and offers Try Again
- Fixed lists from Qwen3-4B that were sometimes left in the wrong language
- Getting a local model ready for your next message is more efficient: the work stops when you leave the list, and the model loads only once
- If the system needs memory and unloads a model while it is still loading, the app now says so and offers Try Again
- Fixed lists from Qwen3-4B that were sometimes left in the wrong language
- Getting a local model ready for your next message is more efficient: the work stops when you leave the list, and the model loads only once
Ver 1.17 2026-11-04
Local models
- Asking a local model to change a list gets an answer sooner
- A local model you choose in Settings starts loading straight away, so your next message waits less
Conversation
- With a hardware keyboard, Return sends your message
- Asking a local model to change a list gets an answer sooner
- A local model you choose in Settings starts loading straight away, so your next message waits less
Conversation
- With a hardware keyboard, Return sends your message
Ver 1.16 2026-10-31
Local models
- When a model finishes downloading while you're using another one, you can switch to it with one tap. If it finishes while the app is in the background, the offer appears when you come back
- When a model is too large for your device, the suggested smaller version prefers one that runs over one that barely runs, and is never below Q3
- A model offered both as one file and as split parts is listed once
- An added model with the same name as a built-in one shows GGUF after its name
- When a model finishes downloading while you're using another one, you can switch to it with one tap. If it finishes while the app is in the background, the offer appears when you come back
- When a model is too large for your device, the suggested smaller version prefers one that runs over one that barely runs, and is never below Q3
- A model offered both as one file and as split parts is listed once
- An added model with the same name as a built-in one shows GGUF after its name
Ver 1.15 2026-10-30
Memory
- Memories are understood more accurately when breaking down a task
- Memories are understood more accurately when breaking down a task
Ver 1.14 2026-10-30
Local models
- On iOS 27 you can add your own GGUF model: in Settings, tap Use your own local model and paste a Hugging Face or ModelScope address. The app checks whether the model runs on your device before you download it
- Nanbeige4.2-3B is no longer built in, and its old download is deleted to free the space. On iOS 27 it is the suggested model in the new sheet, so you can add it again from there. On iOS 26 it is no longer available
- A model that thinks before it answers shows a thinking line while it works. Tap it to read the reasoning
Also fixed
- An English task that mentions your son no longer gets its steps in French
- Tasks written in Traditional Chinese are recognised more reliably, so their steps stay in Traditional Chinese
- On an iPad that can't run Apple Intelligence, the Set up an AI model screen no longer says you need an iPhone 15 Pro
- On iOS 27 you can add your own GGUF model: in Settings, tap Use your own local model and paste a Hugging Face or ModelScope address. The app checks whether the model runs on your device before you download it
- Nanbeige4.2-3B is no longer built in, and its old download is deleted to free the space. On iOS 27 it is the suggested model in the new sheet, so you can add it again from there. On iOS 26 it is no longer available
- A model that thinks before it answers shows a thinking line while it works. Tap it to read the reasoning
Also fixed
- An English task that mentions your son no longer gets its steps in French
- Tasks written in Traditional Chinese are recognised more reliably, so their steps stay in Traditional Chinese
- On an iPad that can't run Apple Intelligence, the Set up an AI model screen no longer says you need an iPhone 15 Pro
Ver 1.13 2026-10-29
Local models
- A failed model download now says why it failed, instead of just "Download failed"
- A download that runs out of storage says so, and Retry continues from where it stopped once you have freed up space
- A failed model download now says why it failed, instead of just "Download failed"
- A download that runs out of storage says so, and Retry continues from where it stopped once you have freed up space
Ver 1.12 2026-10-28
Local models
- Nanbeige4.2-3B is a third model you can download; Qwen3.5-4B stays the recommended one
- The model starts loading as soon as you tap + or open a list, so the first breakdown after launch comes back sooner; the waiting row says "Warming up the model…" meanwhile
Online models
- Custom server: use any server that speaks the OpenAI Chat Completions API, including Ollama on your own Mac over Wi-Fi, with no API key needed
- Save several servers, each with its own address, model ID, nickname and key, and switch between them
- Saved API keys: every key you have stored in one list, with a way to delete one
- A custom server is asked to skip the model's thinking step so replies start sooner, and the server editor shows the exact fields sent
Settings
- The (i) beside Help opens Version & Roadmap: the version you are on, and a thank-you to everyone who has sent feedback
Also fixed
- The online model switched itself off when the app launched before the phone had been unlocked after a restart
- Settings rows animated with Reduce Motion turned on
- The "Try Qwen3.5" bar no longer appears while you are using an online model
- Choosing Apple Intelligence while it was still getting ready switched you to a downloaded model the next time you opened the app
- A list whose reply failed kept saying Apple Intelligence wasn't responding after it started working again
- The "Switch model" button on a list was cut off on iOS 27
- Nanbeige4.2-3B is a third model you can download; Qwen3.5-4B stays the recommended one
- The model starts loading as soon as you tap + or open a list, so the first breakdown after launch comes back sooner; the waiting row says "Warming up the model…" meanwhile
Online models
- Custom server: use any server that speaks the OpenAI Chat Completions API, including Ollama on your own Mac over Wi-Fi, with no API key needed
- Save several servers, each with its own address, model ID, nickname and key, and switch between them
- Saved API keys: every key you have stored in one list, with a way to delete one
- A custom server is asked to skip the model's thinking step so replies start sooner, and the server editor shows the exact fields sent
Settings
- The (i) beside Help opens Version & Roadmap: the version you are on, and a thank-you to everyone who has sent feedback
Also fixed
- The online model switched itself off when the app launched before the phone had been unlocked after a restart
- Settings rows animated with Reduce Motion turned on
- The "Try Qwen3.5" bar no longer appears while you are using an online model
- Choosing Apple Intelligence while it was still getting ready switched you to a downloaded model the next time you opened the app
- A list whose reply failed kept saying Apple Intelligence wasn't responding after it started working again
- The "Switch model" button on a list was cut off on iOS 27
Ver 1.11 2026-08-16
- Added Traditional Chinese: the interface and the AI's steps and replies now support 繁體中文
- Fixed Memory notes written in Traditional Chinese being rewritten in simplified characters
- Fixed Memory notes written in Traditional Chinese being rewritten in simplified characters
Ver 1.10 2026-08-12
- Added DeepSeek, refreshed the online model list to the current Claude and GPT models, and you can now enter a model ID yourself
- Fixed getting stuck on the model setup screen when the online model you picked was no longer in the list, and your lists are readable from that screen now
- You can mark a list as done from the home screen without ticking every step yourself, and in the Done list you can swipe to delete or start a list again from the long press menu
- Deleting a list and marking one as done now animate
- Fixed the answer language for very short input, for French and Spanish, and when your saved Memory notes are in a different language from the task you typed
- Tightened the spacing above the steps inside a list
- Fixed getting stuck on the model setup screen when the online model you picked was no longer in the list, and your lists are readable from that screen now
- You can mark a list as done from the home screen without ticking every step yourself, and in the Done list you can swipe to delete or start a list again from the long press menu
- Deleting a list and marking one as done now animate
- Fixed the answer language for very short input, for French and Spanish, and when your saved Memory notes are in a different language from the task you typed
- Tightened the spacing above the steps inside a list
