Writing and content decision
HyperWrite
A technical user can build a narrow HyperWrite replacement (browser extension + editor + LLM + simple search/citations) using existing APIs and the cited prior-art repo, but reproducing the full product polish, large tool library, Scholar research breadth, and persona/customization would take substantially more engineering and ops work.
Visit website↗$19.99/mo
$240/yr
Read off the official pricing page.
$100one-off80 h to build
$50/mo8 h/mo upkeep
On cash alone, building overtakes the subscription at 3 seats.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All HyperWrite alternatives, with the arithmetic →
What a replacement has to do
- Provide inline autocomplete/typeahead suggestions in a browser editor, accept user prompts and produce rewrites/paragraphs, perform real-time web research to attach citations, and surface results in an editor UI.
What it still won’t have
- Hundreds of pre-made AI tools and templates
- Built-in Scholar research indexed across millions of papers
- Custom personas and multi-persona tuning
- Chrome extension polish and cross-site support
- Priority access to experimental agent features
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 3 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal HyperWrite-like assistant: use Node.js + Express backend, Postgres for user storage, a React web editor, and a Chrome extension content script that calls the backend. Scope in-scope: (1) user sign-up/login (one seat), (2) backend LLM integration via OpenAI API for completions/typeahead, (3) web-retrieval using Bing Search API to gather URLs and attach simple citations, (4) editor UI showing inline suggestions and a chat box for rewrites, (5) basic subscription check (single paid tier) and error handling. Out of scope: multi-persona management, hundreds of premade tools, advanced agent orchestration, large-scale rate limiting, and analytics dashboards. Include automated tests for backend endpoints, unit tests for core editor components, and basic logging and retry logic for external API calls.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 4 cited sources+3
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Evidence score67
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 4
Every page the run actually retrieved.
- official productHyperWrite | AI Writing Assistant
- official pricingPricing | HyperWrite AI Assistant
- open sourceKunAgent/Kun
- open sourcelangchain-ai/local-deep-researcher
Integrity checks
What held up, and what did not.
