Stars
Forks
Watchers
Languagetool
Grammar, punctuation, and style errors a dictionary lookup can't see: LanguageTool is open-source proofreading powered by a Java rule engine covering English, German, Spanish, French, Portuguese, Dutch, and 25+ other languages. Self-hosting the HTTP server is how you get Grammarly-class checking without sending every sentence you write to a third party - a real concern when the text being proofread is confidential email, legal drafts, or unreleased documentation. Your instance exposes the standard /v2/check API, so the official ecosystem plugs straight in: browser extensions for Chrome and Firefox accept a custom server URL, and integrations exist for VS Code, LibreOffice, Obsidian, Vim, Emacs, and many editors. Notably, self-hosting restores free browser-extension checking that the hosted service moved behind a premium subscription - your server, no character limits, no paywall. Detection quality is tunable: optional n-gram datasets (multi-gigabyte language models for en, de, es, fr, nl) teach the engine word-order and confusion-pair errors like there/their and brakes/breaks, and a fastText model improves automatic language identification. Everything runs offline once models are downloaded. The core is LGPL, the API is documented with Swagger, and rules are community- maintained and constantly expanding.
Benefits
- Confidential Text Stays Home
- Legal drafts, private email, and unreleased docs are proofread on your server, never a cloud API.
- No Limits, No Paywall
- Self-hosting removes character caps and restores browser-extension checking without a subscription.
- Works Where You Write
- Browser extensions, VS Code, LibreOffice, Obsidian, Vim, and more connect via the standard API.
- Truly Multilingual
- Rule-based checking for 30+ languages with automatic language detection.
Features
- Grammar and Style Rules
- Thousands of community-maintained rules catching errors spell checkers miss.
- Standard /v2/check API
- Swagger-documented HTTP API compatible with the whole LanguageTool ecosystem.
- N-gram Language Models
- Optional datasets detect confusion pairs and word-order errors like there/their.
- fastText Language Detection
- Accurate automatic identification of the language being checked.
- Fully Offline
- All checking happens locally once models are downloaded - no external calls.
- Editor Integrations
- Chrome, Firefox, VS Code, LibreOffice, Obsidian, Vim, Emacs, and many more.