docs: add inline-scribe to Projects Using Harper#3719
Merged
Conversation
elijah-potter
approved these changes
Jun 25, 2026
elijah-potter
left a comment
elijah-potter
left a comment
Collaborator
There was a problem hiding this comment.
Fantastic! Awesome project. I'm happy to see it. Thank you!
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Following the invitation at the bottom of the "Projects Using Harper" page — adding inline-scribe to the list.
inline-scribe is a Chrome extension (MIT) that proofreads text in any browser field with an on-device LLM (Ollama, or Chrome's built-in Gemini Nano) and shows a Word-style, per-fix accept/reject diff. As of v1.1.0 it integrates Harper as an optional local pre-pass: Harper makes the deterministic, mechanical fixes (capitalization, punctuation, formatting, repetition, agreement) instantly and offline, and the LLM only handles fluency / word choice. Lexical guesses (spelling, typos) are deliberately left to the LLM. It uses
LocalLinter+ the WASM binary, so the pre-pass stays fully on-device.Thanks for Harper — the rule-based, fully-local core is exactly what made it a great pre-pass to build on. Happy to tweak the entry if you'd prefer a different format or placement.