# Build brief — a focused alternative to Grammarly

> **Verdict:** Partly, if you narrow it · **Buildability:** 49/100 · **Category:** AI Writing
> **Source:** https://www.canitbevibecoded.com/grammarly
> Independent editorial assessment from Can It Be Vibe Coded? Not affiliated with, endorsed by, or derived from Grammarly. Verify current pricing and capabilities before acting.

## Context

**Grammarly** — Grammar, clarity, tone, and AI writing assistant across apps. It currently costs $30/mo.

You can build grammar checks and rewrites, but Grammarly's moat is cross-app extensions, inline UX, enterprise controls, writing telemetry, and long-running language quality.

This brief describes a focused, single-operator replacement for the part of Grammarly that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.

## What you are building

Run text through LanguageTool plus an LLM rewrite/tone checker, expose a browser extension or local editor.

- Wrap a model API in a focused drafting, revision, and export workflow.
- A responsive interface with real empty, loading, success, and error states.

## Requirements

### Functional

- Browser extension.
- Optional desktop accessibility layer.
- User dictionary.

### Data and integrations

- Grammar engine/API.
- LLM API.

Each of these needs a real account, credential, or quota. Set them up before writing feature code.

### Non-functional

- Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
- Security: server-side secrets, validated input, and no credentials in the client bundle.
- Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
- Portability: the operator can export their data and leave without losing it.

## Implementation brief

Build me a personal writing checker to replace Grammarly. Requirements:

- Grammar engine: LanguageTool running locally via its official Docker image;
  grammar checks never leave my machine.
- A local web page (Node + Express, binds to localhost): paste text, see
  LanguageTool issues underlined with hover explanations, click a suggestion
  to apply it.
- An LLM rewrite pane (key in .env) with three buttons: tighten, friendlier,
  formal. Show a diff against my original before I accept anything.
- A personal dictionary file (dictionary.txt) of names and jargon to never
  flag, passed to LanguageTool on every check.
- CLI mode: `check <file.md>` prints issues with line numbers, exits nonzero
  if any, so it can run as a git pre-commit hook on docs.
- Everything local except the optional LLM call; no accounts, no telemetry.
- Out of scope: a browser extension and inline suggestions inside Gmail,
  Docs, or Slack. This is a destination I paste into, that is the honest
  trade against Grammarly.
- README: Docker setup for LanguageTool, the roughly 1 GB of RAM it wants,
  and where the LLM key goes.

## Delivery standard

- Inspect the repository first, then write a short implementation plan before writing code.
- Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
- Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
- Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
- Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
- Add structured logs around every external call and return actionable errors without leaking sensitive details.
- Write unit tests for the core logic and one automated test of the main user journey.
- Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.

## Acceptance criteria

- [ ] A clean install starts the app using only the README and .env.example.
- [ ] The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
- [ ] Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
- [ ] The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
- [ ] Tests, type checking, linting, and a production build all pass with no ignored failures.
- [ ] No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.

## Non-goals

Do not build these, and do not claim to have replaced them:

- Inline suggestions everywhere.
- Document/email integrations.
- Tone/brand controls.
- Enterprise admin.
- Connectors, OAuth flows, and vendor API changes require constant upkeep.
- Model quality and inference operations are part of the product.

## What you still own after launch

- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
- Maintain every third-party integration as APIs and OAuth rules change.

## Risk

**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.

Editorial confidence in this assessment: medium. No independent one-shot implementation is linked yet.

## Prior art

Working open-source software you can read, fork, or borrow from before starting:

- [LanguageTool](https://github.com/languagetool-org/languagetool) — Open-source grammar and style checker and the primary Grammarly-like prior art

---

Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/grammarly