llm_localizator
Find the strings your app forgot to translate, translate them with a local or cloud LLM, and
check every placeholder and plural before it ships. One CLI (llm-localizator), a local review
UI, and a CI gate.
On PyPI the package is llm_localizator. It is not related to the llm-localize package on PyPI (a different project).
Your catalogues, glossary and context notes stay in your repository; llm_localizator reads them and writes translations back through the paths you configure.
Why
-
A hardcoded-string finder that measures itself.
agent-hardcodedlists UI text that never went through a translation call, with high, medium or low confidence per hit. It is benchmarked on held-out open-source projects that were never used to tune it, labelled blind. On the latest held-out set macro precision was 0.91 and macro recall 0.34: what it reports is usually right, and it finds about a third of the labelled text outside the mainstream JS/Python/Dart paths. JavaScript, TSX, HTML, Vue, Svelte, Astro, XML UI files and Godot scenes are at the supported tier; 40 languages and formats are scanned in all. Tiers, numbers and known gaps: docs/scanners.md.explain-scan FILE:LINEsays why a line was or was not reported. -
Review like a translation team, not a diff. A local web UI with roles, per-locale assignments, tasks with due dates, approve-only publishing, translation memory, glossary editing, history and back-translation scores, so people review what the model wrote.
-
Pick the engine that fits your budget and hardware. Claude Haiku 5.5 runs every role with no GPU for about $0.12 per 2,300-key locale sweep; DeepSeek and OpenAI are also built in; local Ollama profiles are sized for 4, 8 and 16 GB GPUs and cost nothing.
llm-localizator engine recommendpicks one from your API keys and GPU. -
Built for automation. Every command runs from the CLI or the web UI. Long translation runs can go through a task queue,
check-keysandvalidategate CI with no model, andagent-backlogplus an MCP server give coding agents paste-ready work.
Quick start
pip install llm_localizator
cd your-project
llm-localizator engine recommend # which engine fits this machine
llm-localizator init # write .llm-localize.toml
llm-localizator translate # translate missing and stale keys
llm-localizator validate # placeholders, plurals, glossary (no model)
llm-localizator web # review UI on http://127.0.0.1:8770
Not sure what to do next? llm-localizator guide prints a checklist and the next command.
Details: docs/getting-started.md.
Local engines need Ollama: install it, run ollama serve, then
ollama pull the model the engine names.
Engines
| Engine | Runs on | Notes |
|---|---|---|
claude-haiku |
Cloud, no GPU | About $0.12 per 2,300-key locale sweep; default for cloud projects |
deepseek |
Cloud, no GPU | Best mean back-translation score in a Polish smoke test |
openai |
Cloud, no GPU | Not benchmarked on this pipeline yet |
local-4gb |
Ollama, 4 GB GPU | translategemma:4b for every role |
local-8gb |
Ollama, 8 GB GPU | aya-expanse:8b for every role |
local-16gb |
Ollama, 16 GB GPU | aya translates, qwen2.5:14b scores and improves |
hybrid-local-haiku |
Ollama + cloud | Local translation, Haiku scoring |
llm-localizator engine list shows each engine's evidence status and whether this machine can run
it. Cloud engines never switch cloud on by themselves: they need [privacy] allow_cloud = true
and a monthly budget. See docs/providers.md.
Formats
JSON (nested and flat: i18next, next-intl, react-intl, vue-i18n), YAML (Rails), gettext .po,
Flutter .arb, Android XML, iOS .strings / .stringsdict / .xcstrings, XLIFF, .resx,
Java .properties, Qt .ts, Laravel and PHP arrays, go-i18n, Chrome extension messages and CSV.
ICU is the interchange model, so validation and prompts see one shape whatever is on disk:
docs/catalog-adapters.md.
Documentation
| Topic | Doc |
|---|---|
| First project, step by step | docs/getting-started.md |
| Every command and flag | docs/cli.md |
.llm-localize.toml reference |
docs/configuration.md |
| Hardcoded-string scanner | docs/scanners.md |
| What each validation rule checks | docs/validation-rules.md |
| Catalogue formats and plural bridging | docs/catalog-adapters.md |
| Providers and engines | docs/providers.md |
| The web interface | docs/web.md |
| CI integration | docs/ci.md |
| Coding agents and MCP | docs/agents.md |
| Browser runtime for plain JS apps | docs/web-runtime.md |
| Queue integration | docs/taskqueue-integration.md |
| Choosing and comparing models | docs/model-evaluation.md |
| Design decisions | docs/decisions/ |
Transparency
- No telemetry, no phone-home.
validate,scan,status,check-keysandagent-hardcodedare local computation with no network access. - Text leaves your machine only when you choose a cloud engine and enable it with
[privacy] allow_cloud = trueand a budget. API keys are read from the environment. - The review server binds to
127.0.0.1and needs a per-session token for every write. See SECURITY.md.
Contributing
Issues and PRs are welcome: CONTRIBUTING.md. The default test run is
hermetic (no model, no GPU, no network): uv run pytest.
License
Metadata
Release files for llm-localizator 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| llm_localizator-0.2.0.tar.gz | 4.0 MB | Without provenance | Details for llm_localizator-0.2.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| llm_localizator-0.2.0-py3-none-any.whl | Python 3 | none | any | Details for llm_localizator-0.2.0-py3-none-any.whl |
Total release size: 5.9 MB
Release files / llm_localizator-0.2.0.tar.gz
| Download URL | llm_localizator-0.2.0.tar.gz |
|---|---|
| Size | 4.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fdab13aee0b03bc99b9538b474076d91dfe1ac4c1d3bdec4455e0fa3900dd0ba
|
|
BLAKE2b-256 checksum How to use checksums |
d73f7d7fcc1bd6e45b24c892aae2dae38582c71f9e5e8fc520ab3483710b9da1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.11
|
Release files / llm_localizator-0.2.0-py3-none-any.whl
| Download URL | llm_localizator-0.2.0-py3-none-any.whl |
|---|---|
| Size | 1.9 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
60119d876b641c66d1b44826cfcd24eedee2918cdde3dc0663d76ac5bbe00271
|
|
BLAKE2b-256 checksum How to use checksums |
2ccec962b0307fa9fb0e87fe02fb33624c04a167f0e857aa5011d2809fd8bcd5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.11
|
Security for llm-localizator 0.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.