NVIDIA-NeMo / Anonymizer
🕵️ NeMo Anonymizer: Detect and protect PII through context-aware replacement and rewriting
Why this job: works in the areas we cover, but does not say which job it does
What it does
By default, Anonymizer expects a compatible local GLiNER2 endpoint for entity detection and uses text LLMs hosted on OpenRouter for augmentation and validation. The tutorial notebooks can start the local detector automatically. You can also bring your own models via custom provider configs.
Get started
pip install nemo-anonymizerYou need: Python 3.11+; NeMo Data Designer (installed as dependency); A compatible local GLiNER2 endpoint (the tutorial notebooks can start one automatically)
- Maintenance
- Active
- Last commit yesterday
- Stars
- 137
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.5.0
- Released 15 days ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- 9
- Last 90 days
- Issues
- 57% closed
- 44 still open
- Pull requests
- 234 merged
- 35 waiting
- Releases
- 12
- 12 in the last year
More: languages, topics and project record
Languages
- Python 99%
- Shell <1%
- Makefile <1%
- Standard ML <1%
Topics
- anonymization-pipeline
- contextual-privacy
- llm
- nvidia
- nvidia-nemo
- pii-anonymization
- sdg
Project record
- JobOther AI tools
- StatusListed
- Commits197
- Forks22
- Watching0
- Stars in 28 days+11
- CreatedJan 20, 2026
- First seen by usNov 7, 2026
- CheckedNov 12, 2026