A fully private writing aid for Mac that suggests the next words as you write
Datasets for RAG, fine-tuning and training built from public sources
Stage
MVP
Not given
Founded
2026
Not given
Based in
FR
Not given
Pricing model
Paid
Paid
Pricing
Free download. Studio license: €29 with Lightning, €39 by card. One-time purchase, no subscription.
Web Corpus: starter sets from $49 (250,000-500,000 documents); shelf corpora from $99-$199 per shelf (one-time license); Everything (full crawl) $3,000 one-time; Whole Library (all builds for one year) $5,000 per year. Reference Collections: Encyclopedia $1,200 commercial or $349 research (one-time)
Key features
Real-time text suggestions under cursor
Learns your writing style over time
Tone adjustment with '//' command
Translation while typing
Automatic typo correction
Emoji picker with keyboard shortcut
Usage ledger tracking keystrokes saved
Works offline after initial setup
Runs in Mail, Notes, Messages, Safari and most Mac apps
Encrypted local history
Web corpus with 100.7M documents and 105B tokens from Common Crawl
Documents scored with Bear Rank and shelved by subject
15 million encyclopedia entries with sources and model attribution
200 million synthetic Q&A records with metadata
Delivered as JSONL and Parquet formats
Free samples available on Hugging Face
Command-line client with resumable downloads and SHA-256 verification
Statistics collection with 7,000 topics and 140,000 figures
Glossaries for 10,000 topics with one million definitions
Book Q&A dataset with 8,000 titles for reading comprehension
What makes it different
One-time purchase with no subscription or daily limits
Learns your personal style and tone
Works offline in any Mac app
Built-in translation for multiple languages
All datasets built only from public sources with full provenance tracking
Every record includes source attribution and licensing information
Eight curated subject shelves for targeted corpus selection
Flexible purchasing: buy individual shelves, slices, or entire library
Over 4 TB of clean, deduplicated text ready for machine learning
Souffleuse