Desktop app that transcribes audio and video fully offline on your own device, using Whisper and other speech models.
AashishH15/Lexicon
A local-first desktop writing assistant that proofreads, rewrites, and exports drafts without sending text to any server.
Open-source alternative to:Grammarly
- Stars
- 220
- Forks
- 19
- Open issues
- 0
- Last commit
- 4 days ago
What is it?
Lexicon is a distraction-free rich-text editor for Windows, macOS and Linux. It combines inline grammar and spelling checks powered by LanguageTool with a review panel where suggestions can be applied or dismissed. Tone detection and a clarity score help assess drafts.
The app includes local AI tools for rewriting, concise edits, tone adjustments such as formal or friendly, and summary, key point, list and table transforms. A bundled llama.cpp backend runs a downloadable model on the device, and an existing local Ollama server can be used instead. No account is required, and documents are auto-saved in local browser storage.
Writing can be imported from TXT, Markdown and HTML files and exported as HTML, plain text, Markdown or PDF. The editor also supports tables, code blocks, LaTeX math, and a personal dictionary for words that should not be flagged.
Key features
- 01Inline grammar and spelling checks via local LanguageTool
- 02Review panel to apply, dismiss, or accept suggestions in bulk
- 03Local AI rewrite, concise, and tone tools using llama.cpp or Ollama
- 04Summary, key points, list, and table transforms for whole documents
- 05Import TXT, Markdown, and HTML; export HTML, text, Markdown, or PDF
- 06Auto-save and personal dictionary with no account required
Use cases
- Proofreading drafts that contain confidential or private material
- Rewriting emails or documents in a more formal or friendly tone
- Turning long drafts into summaries or key-point outlines
- Writing offline on a laptop without a cloud writing service
Quick start
- 1
Download the installer for your OS from the latest GitHub release
- 2
From the project root, run the start script (macOS/Linux)
./start.sh - 3
On Windows, run the start script instead
.\start.bat - 4
Open the local frontend in your browser
http://localhost:5173
Things to know
- The macOS build is unsigned and may be blocked by Gatekeeper on first launch.
- Windows builds are not code-signed, so SmartScreen or antivirus warnings may appear.
- Running from source requires Python 3, Node.js with npm, and Java for the LanguageTool backend.
Topics
FAQ
- What is Lexicon?
- A local-first desktop writing assistant that proofreads, rewrites, and exports drafts without sending text to any server. Lexicon is a distraction-free rich-text editor for Windows, macOS and Linux. It combines inline grammar and spelling checks powered by LanguageTool with a review panel where suggestions can be applied or dismissed. Tone detection and a clarity score help assess drafts.
- Is Lexicon free to use? What license does it have?
- Lexicon is open source under the MIT license. Check the license terms before using it in commercial products.
- Is Lexicon still maintained?
- Actively maintained. The last commit to Lexicon was on Oct 16, 2026.
- What can I use Lexicon for?
- Proofreading drafts that contain confidential or private material Rewriting emails or documents in a more formal or friendly tone Turning long drafts into summaries or key-point outlines Writing offline on a laptop without a cloud writing service
- How do I install Lexicon?
- Download the installer for your OS from the latest GitHub release From the project root, run the start script (macOS/Linux): ./start.sh On Windows, run the start script instead: .\start.bat Open the local frontend in your browser: http://localhost:5173
- Where can I get Lexicon?
- The source code and installation instructions are on GitHub: https://github.com/AashishH15/Lexicon
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A self-hosted, privacy-focused alternative to Google's NotebookLM for chatting with your sources and generating podcasts, with support for many AI providers.
Open-source document parser that converts PDF, Office, HTML and other files into structured data for generative AI pipelines.
An open source, general-purpose AI agent that runs on your machine as a desktop app, CLI, or embeddable API, for code and non-code tasks.
Open-source desktop agent app and Rust library for running many AI agents with lower token use, memory and resource cost.
A local-first, Markdown-native long-term memory layer for AI agents, storing memories as editable files with SQLite and LanceDB indexes.