YOUR NEXT IDEA STARTS HERE

Read papers,
effortlessly.

Original paper. Translation under every paragraph. Answers you can trace. Meet the research companion that keeps you in the flow.Your AI paper reader for Mac. Translate side by side, ask with citations, and keep Markdown notes.

For Mac · Install and read on your Mac

Local-first · Bring your own AI · One-time purchase

Inside ReadArcmacOS today · Windows in development
ReadArc side-by-side view of Attention Is All You Need: the original page next to its Chinese translation, with answers citing paragraphsView full screenshot
The paper, the explanation and your next question. Together.
Your PDFs, on your computerYour model, your choiceYour notes, in Markdown

STAY WITH THE PAPER

Everything you need.
Right where you read.

Follow the argument, check an equation, capture an idea. Keep the context while you do it.

OriginalAttentionis all you need.
↔
译文注意力机制就是你所需要的一切。
01 / Bilingual reading

Read between the languages.

Read the original and translation paragraph by paragraph. arXiv papers use the official HTML version for sharper formulas and figures, and the original PDF layout is one click away.

What is the core idea?

The Transformer uses attention to connect relevant parts of a sequence, without recurrence.

Abstract · p. 1 ↗Illustrative answer
02 / Answers with references

Good questions deserve sources.

Ask about a passage or a screenshot. Follow paragraph citations back to the paper and check the reasoning yourself.

↳ notes.md

# An idea for the next experiment

Compare attention patterns across longer sequences.

Saved as Markdown
03 / Notes you own

An idea worth keeping.

Highlight a passage and add a note. Notes are plain Markdown files you can open in your own editor.

SAME PAPER. A DIFFERENT WAY IN.

A little personality.
A lot more clarity.

Some days you want the details. Some days you just want someone to explain it like you’re eight. Pick your way in.

Swipe to explore reading modes

ReadArc / Reading modes•••
How does attention work?
ReadArc Grandma mode

Think of attention as looking something up in a filing cabinet. You come with a question, and each folder has a label on the front and papers inside. You compare your question to every label to see how well it matches, and then you build your answer by mixing the papers together — taking a lot from the folders whose labels matched well and only a little from the others§3.2.

In this paper, the matching is done by a simple comparison of the question with each label, and then the match scores are shrunk a bit before they are turned into the mixing amounts§3.2.1. That shrinking matters: without it, when the labels are long and detailed, the scores get so big that the whole thing becomes hard to train.

They also do this several times side by side, each copy looking at things in its own way, and then join the results — so the model can pay attention to different kinds of information at once§3.2.2.

Answers generated by Claude Opus 5, shown unedited

YOUR RESEARCH. YOUR SETUP.

Bring the model.
Keep the freedom.

Connect your own API key or a model running on your own computer. Choose models by task and keep an eye on estimated usage.

PDFs and notes are stored locally. Cloud AI sends the content needed for your request to the service you configure.

CHOOSE YOUR INTELLIGENCE
Cloud modelOpenAI · Claude · GeminiLocal modelOllama · LM Studio
ReadArc↙   ↘
Your API keyYour computer

LESS FILE HUNTING

A home for the papers
you actually read.

Find papers on arXiv, Semantic Scholar and OpenAlex and add them to your library. Titles are translated, authors fill in automatically, and pins and tags keep things sorted. Pick up where you left off.

arXivSemantic ScholarOpenAlexPDF

GET READARC

Install. Open. Read.

A one-time purchase on the Mac App Store. No subscriptions, no bundled token markup.

MAC APP STORE

ReadArc for Mac

The ready-to-use macOS app, with installation and updates through the App Store.

CNY 18one-time purchase
US$2.99 in the US. Prices vary by region. Cloud model API usage is billed separately.
  • Signed, sandboxed Mac app
  • Updates through the App Store
  • All features included — no subscriptions
Get it on the Mac App StoreGet the Mac app

macOS is available now on the Mac App Store. A Windows version is in development.

FAQ

A few things worth knowing.

Do I need an AI subscription?

ReadArc uses API access from the provider you choose, or a local model. Cloud API usage is billed separately by that provider; a chat-app subscription may not include API access.

Can I read without an internet connection?

Yes. Imported PDFs, saved translations, the bundled dictionary and notes work offline. Cloud AI and online paper search need a connection.

Does ReadArc upload my whole library?

No. Your library is stored on your computer. When you use a cloud AI feature, the content needed for that task is sent to your configured endpoint. A local gateway may also forward requests to the cloud.

What does ReadArc cost?

The Mac App Store version is a one-time purchase: CNY 18 in China, US$2.99 in the US. Other regions follow the store price, with no subscriptions or in-app purchases. Cloud model API usage is billed separately by your chosen provider.

Which computers are supported?

macOS is available now on the Mac App Store. A Windows version is in development.

READ. QUESTION. CONNECT.

The next good idea
is waiting in a paper.

Give it a little attention.

Get it on the Mac App StoreGet the Mac app

Zoom in, then scroll to explore the interface.