HN Showcase
Back to browse
GitHub Repository

Cache-driven incremental translation (via LLM, GoogleTranslate, etc.)

5 starsTypeScript

Transly – Cache-driven incremental translation

by vitonsky·Apr 29, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemCozy

Content-hash caching beats git-diff approaches for incremental i18n translation.

Strengths
  • •SHA-256 hashing per string ensures only modified content triggers API calls.
  • •Writes cache after every chunk so partial failures never lose completed work.
  • •Pluggable backend supports any LLM or free translation service without lock-in.
Weaknesses
  • •No Windows support mentioned; likely Unix-centric given the tooling stack.
  • •Competes with established i18n platforms like Lokalise and Crowdin that offer GUIs.
Target Audience

Frontend developers managing multi-language applications

Similar To

Lokalise · Crowdin · i18next

Similar Projects

Developer Tools●●Solid

Node.js LLM internationalization compiler: Scan code and Auto-Translate

It hooks into your build process, finds t(...) calls, and only generates missing translations via an LLM while preserving hand-edited entries — useful ergonomics many i18n tools skip. Comes with Vite/Webpack plugins, watch/batching modes and unused-key cleanup; the hard parts left to you are translation quality, API cost, and secrets management.

Solve My ProblemNiche Gem
mfcmatheus
204mo ago