Quickstart

Goal

Create an i18n.yml, run translation planning safely, generate outputs, and review status.

1. Initialize config

hyperlocalise init

This writes i18n.yml in your current directory.

2. Configure provider credentials

hyperlocalise automatically reads credentials from .env and .env.local in your current project directory. Exported shell variables still take precedence. Example:

export OPENAI_API_KEY="your-openai-api-key"

OPENAI_API_KEY="your-openai-api-key"

OpenAI:

export OPENAI_API_KEY="your-openai-api-key"

OPENAI_API_KEY="your-openai-api-key"

Azure OpenAI:

# Example: https://<resource>.openai.azure.com/openai/v1
export AZURE_OPENAI_BASE_URL="https://<resource>.openai.azure.com/openai/v1"
export AZURE_OPENAI_API_KEY="your-azure-openai-api-key"

# Example: https://<resource>.openai.azure.com/openai/v1
AZURE_OPENAI_BASE_URL="https://<resource>.openai.azure.com/openai/v1"
AZURE_OPENAI_API_KEY="your-azure-openai-api-key"

Gemini:

export GEMINI_BASE_URL="https://generativelanguage.googleapis.com/v1beta/openai"
export GEMINI_API_KEY="your-gemini-api-key"

GEMINI_BASE_URL="https://generativelanguage.googleapis.com/v1beta/openai"
GEMINI_API_KEY="your-gemini-api-key"

Anthropic:

export ANTHROPIC_BASE_URL="https://api.anthropic.com/v1"
export ANTHROPIC_API_KEY="your-anthropic-api-key"

ANTHROPIC_BASE_URL="https://api.anthropic.com/v1"
ANTHROPIC_API_KEY="your-anthropic-api-key"

LM Studio:

export LM_STUDIO_BASE_URL="http://127.0.0.1:1234/v1"
export LM_STUDIO_API_KEY="lm-studio"

LM_STUDIO_BASE_URL="http://127.0.0.1:1234/v1"
LM_STUDIO_API_KEY="lm-studio"

Ollama:

export OLLAMA_BASE_URL="http://127.0.0.1:11434/v1"
export OLLAMA_API_KEY="ollama"

OLLAMA_BASE_URL="http://127.0.0.1:11434/v1"
OLLAMA_API_KEY="ollama"

Groq:

export GROQ_BASE_URL="https://api.groq.com/openai/v1"
export GROQ_API_KEY="your-groq-api-key"

GROQ_BASE_URL="https://api.groq.com/openai/v1"
GROQ_API_KEY="your-groq-api-key"

3. Dry-run first

hyperlocalise run --dry-run

Check planned_total, executable_total, and the listed tasks.

4. Execute generation

hyperlocalise run

This writes translations and updates .hyperlocalise.lock.json. For details, see Lockfile contract.

5. Review status

hyperlocalise status --output csv

Use needs_review rows to identify entries that still need human curation.

6. Evaluate translation quality when needed

hyperlocalise eval run --eval-set ./eval-set.json --output ./eval-report.json

Use this when comparing prompt/profile/provider choices or before promoting large translation updates.

Tune config in i18n config.
Sync with your TMS using sync push and sync pull.
Check maturity expectations in the stability matrix.

Getting Started

Configuration

Commands

Workflows

Providers

TMS Adapters

Troubleshooting

Reference & Concepts

Contributing

Legal

Goal

1. Initialize config

2. Configure provider credentials

3. Dry-run first

4. Execute generation

5. Review status

6. Evaluate translation quality when needed

Next

​Goal

​1. Initialize config

​2. Configure provider credentials

​3. Dry-run first

​4. Execute generation

​5. Review status

​6. Evaluate translation quality when needed

​Next

Goal

1. Initialize config

2. Configure provider credentials

3. Dry-run first

4. Execute generation

5. Review status

6. Evaluate translation quality when needed

Next