Provides a GitHub Action that validates catalogs, translates the delta, commits catalogs and the lockfile to pull request branches, and keeps a PR comment updated with coverage, issues, and cost.
Works with i18next catalogs, validating i18next syntax, placeholders, plural categories, and glossary terms while translating missing or stale strings.
Supports Ollama as an OpenAI-compatible local endpoint for running translations without relying on external API keys.
Integrates with OpenAI and OpenAI-compatible endpoints as an LLM provider for translations, configurable via the OpenAI API key.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Your coding agent localizes your app. Deterministic code guarantees that nothing broken or too long lands in your catalogs.
The real glot translate binary. The LLM is scripted to get three strings wrong on its first pass; every refusal and message is glot's. Reproduce it, or rerun it with a real model doing the retries: docs/launch/record/refusal.sh.
npx glot-i18n init # detect your i18n stack, write glot.toml + rules for your coding agent
npx glot-i18n i18nize # hardcoded UI strings -> keys, components rewritten (next-intl, react-i18next)
npx glot-i18n translate # translate only the delta; invalid output is refused, retried, never writtenOr all of it in one idempotent step: npx glot-i18n localize --yes --targets fr,de (init if needed → i18nize → translate → check).
Checked by code on every LLM output, on glot set, in the overlay and in CI (glot check). A refused string goes back to the model with the exact reason (2 retries, then the fallback model); if it still fails, nothing is written.
Placeholders |
|
CLDR plurals | Every category the target locale needs ( |
Glossary |
|
Pixel width |
|
Lockfile |
|
MCP for your agent |
|
Works with the i18n library you already use, adds no runtime, bring your own LLM key (Anthropic, OpenAI, any OpenAI-compatible endpoint). MIT.
More: Docs (concepts, CLI, MCP, integrations & GitHub Action, agent skill, AI-translation provenance, FAQ & costs) · Labs (SEO, database content, emails/images, task parity, plural coverage…) · Self-hosted server (experimental) · Demo app · Architecture
This server cannot be deployed
Localize iOS and Android apps: coverage, missing strings, glossary-aware AI drafts and file sync.
Localize apps from your AI assistant: translate locale files, set glossaries, connect GitHub repos.
Agentic localization for documents and media, with quality checks and optional human review.
Live React design-system APIs, patterns, and code validation so AI agents build real UI, not slop.
