npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@llmtr/core

v0.0.3

Published

Core AI translation API for llmtr — reusable across tools

Readme

@llmtr/core

Core AI translation API for llmtr — reusable across tools.

This package provides the translation engine, config discovery, provider abstraction, and file watcher used by @llmtr/cli. It is designed to be embedded in any Node.js tool that needs AI-powered translation.

Install

npm install @llmtr/core

Providers

| Provider | Default Model | Env Var | |---|---|---| | openai | gpt-4o | OPENAI_API_KEY | | anthropic | claude-3-5-sonnet-20241022 | ANTHROPIC_API_KEY | | google | gemini-1.5-pro | GOOGLE_API_KEY | | mistral | mistral-large-latest | MISTRAL_API_KEY | | deepseek | deepseek-chat | DEEPSEEK_API_KEY |

API keys are read from the matching environment variable when not provided explicitly.

Usage

Translate text

import { createLanguageModel, Translator } from '@llmtr/core'

const model = createLanguageModel({ provider: 'openai' })
const translator = new Translator(model)

const results = await translator.translate('Hello, world!', {
  targetLanguages: ['zh-CN', 'ja', 'fr'],
})

for (const r of results) {
  console.log(r.language, r.text)
}

Translate a file

const results = await translator.translateFile('./README.md', {
  targetLanguages: ['zh-CN', 'ja'],
  outputDirectory: './i18n',
  fileNamePattern: '{name}.{lang}{ext}', // e.g. README.zh-CN.md
})

Streaming events

await translator.translateWithStream(
  'Good morning',
  { targetLanguages: ['de', 'es'] },
  (event) => {
    if (event.type === 'delta')
      process.stdout.write(event.delta)
    if (event.type === 'done')
      console.log('\nDone:', event.language)
  },
)

Watch a file

import { createWatcher } from '@llmtr/core'

const handle = createWatcher('./content.md', (filePath) => {
  console.log('changed:', filePath)
  // re-run your translation here
}, { debounce: 500 })

// Later:
await handle.stop()

Config discovery

loadTranslationConfig walks the directory tree from cwd up to ~ and merges the nearest config with defaults and explicit overrides.

import { loadTranslationConfig, validateConfig } from '@llmtr/core'

const config = await loadTranslationConfig(process.cwd(), {
  provider: 'openai', // CLI flag — highest priority
})

validateConfig(config) // throws if provider or targetLanguages are missing

Config file names searched (in order):

  • llmtr.config.json
  • .llmtr.config.json
  • .llmtrrc.json / .llmtrrc
  • llmtr.config.js / .mjs / .ts
  • package.json"llmtr" key

Global config: ~/.llmtr.config.json

Locales

import { fetchLocales } from '@llmtr/core'

const locales = fetchLocales() // synchronous, no network request
// [{ locale: 'zh-CN', language: { name: 'Chinese', ... }, country: { name: 'China', ... } }, ...]

Config Schema

interface TranslationConfig {
  provider: 'openai' | 'anthropic' | 'google' | 'mistral' | 'deepseek'
  apiKey?: string // falls back to env var
  model?: string // falls back to provider default
  baseURL?: string // OpenAI-compatible custom endpoint
  sourceLanguage?: string // auto-detected when omitted
  targetLanguages: string[]
  systemPrompt?: string
  output?: {
    directory?: string
    fileNamePattern?: string // default: '{name}.{lang}{ext}'
  }
  watch?: {
    debounce?: number // default: 500ms
  }
}

API

| Export | Description | |---|---| | Translator | Core translation class | | createLanguageModel(config) | Create a Vercel AI SDK LanguageModel | | hasApiKey(config) | Check whether an API key is available | | loadTranslationConfig(cwd?, overrides?) | Load and merge config from file + overrides | | validateConfig(config) | Assert config has required fields | | createWatcher(file, translator, options) | Watch a file and re-translate on change | | fetchLocales() | Return bundled list of locale entries | | checkNetwork(targetUrl?) | Verify connectivity to a URL (defaults to generic IPs) | | getProxyUrl() | Return the effective proxy URL from env vars, or undefined | | hasEmptyProxyVar() | Detect export PROXY= (set to empty string instead of unset) | | GLOBAL_CONFIG_PATH | Path to ~/.llmtr.config.json | | CONFIG_DEFAULTS | Default config values | | DEFAULT_MODELS | Default model per provider | | PROVIDER_BASE_URLS | Canonical API base URL per provider | | ENV_API_KEYS | Env var name per provider |

License

MIT © Moozon