llm-powered multi-format static file translation with provider abstraction
Translates static content files (JSON, YAML, CSV, PO, Markdown) by parsing them into an intermediate representation, routing translation requests through a pluggable LLM provider layer (Lingo.dev Engine, OpenAI, Anthropic, Google, Mistral, OpenRouter, Ollama), and writing localized output files with an i18n.lock manifest tracking translation state. The compiler uses AST-aware parsing per format to preserve structure and metadata during round-trip translation.
Unique: Implements a provider abstraction layer that allows swapping between 6+ LLM backends (Lingo.dev Engine, OpenAI, Anthropic, Google, Mistral, OpenRouter, Ollama) without code changes, combined with format-specific AST-aware parsers that preserve file structure and metadata during translation rather than naive string replacement.
vs alternatives: Offers more LLM provider flexibility and format support than traditional i18n tools like i18next or react-intl, while maintaining deterministic, reproducible translations via lock files unlike manual translation services.
build-time jsx/tsx compiler with localization injection and code splitting
Integrates into Next.js, Vite, or webpack build pipelines via withLingo() wrapper or lingoCompilerPlugin() to intercept JSX/TSX source files, extract translatable strings, invoke LLM translation, and inject localized content into separate .lingo/ cache bundles per locale. The new compiler (@lingo.dev/compiler) uses AST transformation to rewrite component imports and string literals, enabling zero-runtime overhead for static translations while maintaining source map fidelity.
Unique: Uses AST-aware code transformation to inject localized content directly into compiled bundles at build time, eliminating runtime translation overhead and enabling per-locale code splitting, rather than runtime string lookup tables used by traditional i18n libraries.
vs alternatives: Faster than react-intl or next-i18next at runtime (zero translation latency) and smaller bundle sizes per locale than shipping a single translation dictionary, but requires longer build times due to LLM API calls.
react component localization with hooks and context providers
Provides React-specific bindings (in @lingo.dev/react package) including hooks (useLocale, useTranslate) and context providers that integrate Lingo.dev translations into React component trees. The React package wraps the SDK to provide idiomatic React patterns, enabling components to access current locale, trigger locale switches, and subscribe to translation updates without prop drilling.
Unique: Provides idiomatic React hooks (useLocale, useTranslate) and context providers that integrate Lingo.dev translations into React component trees, enabling locale switching and translation access without prop drilling or HOCs.
vs alternatives: More React-idiomatic than generic SDK usage; comparable to react-intl but with LLM-powered translation and simpler API for basic use cases.
translation state tracking with i18n.lock manifest and incremental updates
Maintains an i18n.lock manifest file that tracks the translation state of every string (which strings have been translated, which are pending, which have changed since last translation). The lock file enables incremental translation workflows where only changed or new strings are re-translated, reducing API costs and improving CI/CD performance. Lock file is version-controlled alongside source code, providing an audit trail of translation history.
Unique: Implements an i18n.lock manifest that tracks translation state per string, enabling incremental translation workflows where only changed strings are re-translated, reducing API costs and improving CI/CD performance while providing an audit trail.
vs alternatives: More cost-efficient than re-translating all strings on every run; comparable to lock files in package managers (package-lock.json, yarn.lock) but for translation state rather than dependencies.
runtime sdk for dynamic string localization with fallback chains
Provides a JavaScript/TypeScript SDK (npm install lingo.dev) that localizes strings, objects, and HTML at runtime by querying a locale-aware translation store with automatic fallback chains (e.g., en-US → en → default). The SDK manages locale state, caches translations in memory, and supports both synchronous lookups for pre-compiled translations and async calls for dynamic content, with built-in support for pluralization and interpolation patterns.
Unique: Implements automatic fallback chains with configurable locale hierarchies (e.g., en-US → en → default) and in-memory caching of translations, allowing runtime locale switching without page reloads or rebuilds, combined with support for both pre-compiled and dynamic translations in a single API.
vs alternatives: More flexible than static i18n libraries (i18next, react-intl) for dynamic content, but slower at runtime than build-time compiled translations; better suited for hybrid scenarios with both static and dynamic localization needs.
cli with multi-format file discovery and batch translation orchestration
Command-line interface (npx lingo.dev@latest run) that recursively discovers translatable files in a project (JSON, YAML, CSV, PO, Markdown), batches them for efficient LLM processing, orchestrates the translation pipeline, and writes localized output files alongside an i18n.lock manifest. The CLI uses a configuration file (i18n.json) to define source directories, target locales, and provider settings, with support for dry-run mode and incremental translation (only translating changed files since last run).
Unique: Implements recursive file discovery with format-specific loaders, batching optimization for LLM API efficiency, and incremental translation tracking via i18n.lock manifest, allowing teams to translate entire projects in a single command while maintaining reproducibility and auditability.
vs alternatives: More automated than manual translation workflows or spreadsheet-based tools, and more flexible than single-file translation tools; comparable to Crowdin or Lokalise but with LLM-driven automation and no vendor lock-in.
mcp server for ai agent-driven i18n configuration and routing
Exposes Lingo.dev as a Model Context Protocol (MCP) server that allows AI agents and IDEs to prompt for i18n needs in natural language and receive generated routing, middleware, and configuration boilerplate. The MCP server translates high-level i18n requirements (e.g., 'support 10 languages with fallback to English') into concrete code artifacts (Next.js middleware, locale routing, provider configuration) without requiring manual setup.
Unique: Implements an MCP server that translates natural language i18n requirements into concrete code artifacts (routing, middleware, configuration), enabling AI agents to scaffold multilingual projects without requiring developers to understand framework-specific i18n patterns.
vs alternatives: Unique to Lingo.dev as an MCP-first i18n tool; traditional i18n libraries require manual setup, while this enables AI-assisted scaffolding for faster project initialization.
github actions ci/cd integration with automatic translation on push
GitHub Action (uses: lingodotdev/lingo.dev@main) that triggers on git push to main, automatically translates changed content files, and commits translated files back to the repository or opens a pull request with translations. The action integrates with GitHub Workflows, caches translation results to avoid redundant API calls, and supports conditional triggers (e.g., only translate if specific files changed).
Unique: Implements a GitHub Action that automatically translates content on push and commits results back to the repository or opens a PR, integrating continuous localization directly into CI/CD workflows without requiring separate translation services or manual steps.
vs alternatives: More integrated with GitHub workflows than external translation services (Crowdin, Lokalise) and cheaper than SaaS localization platforms for teams already using GitHub; requires more setup than manual translation but eliminates manual file management.
+4 more capabilities