Translate a React or Vue app's JSON locale files into multiple Indian languages automatically.
Batch translate markdown or MDX documentation pages for a localized website.
Keep a multilingual site's content up to date by only translating newly added text.
Build a Next.js site that serves content in several Indian languages using next-intl.
| sarvam-ai/localize | atomicstrata/atomicmemory | azerdsq131/mcpm | |
|---|---|---|---|
| Stars | 6 | 6 | 6 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | easy | moderate | easy |
| Complexity | 2/5 | 4/5 | 2/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires a free Sarvam AI API key set in a .env file before translating anything.
Sarvam Localize is a command line tool for translating a website's text into Indian languages. It is built on top of Sarvam AI's own translation service, and it is aimed at developers who need to localize a website's JSON locale files or markdown content pages without doing the translation by hand. To use it, a developer first gets a free API key from Sarvam AI's dashboard and puts it in a local environment file. From there the tool can be run directly with npx, no separate install step needed. Running an init command creates a config file that records settings like which language the source content is written in and which languages to translate it into, so future runs do not need those options typed out again. The tool handles two kinds of content differently. For JSON locale files, commonly used by internationalization libraries like React i18next or Vue i18n, it translates the text values while preserving the nested key structure and any placeholder variables inside the strings, such as a person's name being inserted into a greeting. For markdown or MDX content pages, it scans a source folder for files matching a chosen naming pattern and writes translated copies into a destination folder, organized by language. The list of supported languages is large and specific to India, covering Hindi, Bengali, Gujarati, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, and Telugu with one underlying model, and an even longer list including Assamese, Urdu, Nepali, Sanskrit, and several other regional languages with a second, broader model. By default the tool skips any text that has already been translated, so repeated runs only fill in new or missing content, though a redo flag can force everything to be retranslated. Two working demo websites built with Next.js show the tool's output in practice.
A command line tool that automatically translates a website's JSON locale files and markdown pages into Indian languages using Sarvam AI's translation service.
Mainly TypeScript. The stack also includes TypeScript, Node.js, Sarvam AI API.
No license information is stated in the README.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.