NVIDIA-NeMo/Anonymizer

View on GitHub

🕵️ NeMo Anonymizer: Detect and protect PII through context-aware replacement and rewriting

Stars: 122
Forks: 17
Open beginner issues: 0
Indexed issues: 27
Avg merge: 4d 2h
Merged PRs (30d): 11

Dominant language: Python
License: Apache-2.0
Last GitHub push: Sep 18, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: No beginner labels indexed

Beginner friendly Everything

Open All

27 open issues indexed

Rewrite quality checks allow grammatically malformed generalizations Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 48/100

NVIDIA-NeMo/Anonymizer#276 · Opened Sep 17, 2026
Normalize null judge detail lists only for positive verdicts Open

NVIDIA-NeMo/Anonymizer#270 · 1 assignee · Opened Sep 15, 2026
feat(detection): add regex and validator entity detection Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA-NeMo/Anonymizer#262 · Opened Sep 8, 2026
Expose per-label detection examples in the public configuration API Open

enhancement

NVIDIA-NeMo/Anonymizer#259 · 3 comments · 1 assignee · Opened Sep 2, 2026
Implement private Phase 7 stable Substitute planning Open

task

Difficulty 5/5 Over a week Newbie friendliness 15/100

NVIDIA-NeMo/Anonymizer#257 · 17 comments · Opened Aug 31, 2026
feat(dev): add managed local model serving tool Open

task

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA-NeMo/Anonymizer#252 · Opened Aug 18, 2026
design: group evaluation provenance in result objects Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA-NeMo/Anonymizer#251 · Opened Aug 17, 2026
fix: preserve validated entity provenance on exact-span augmentation conflicts Open

Difficulty 3/5 1-2 days Newbie friendliness 76/100

NVIDIA-NeMo/Anonymizer#250 · Opened Aug 14, 2026
make check reports many type failures Open

task

Difficulty 4/5 3-5 days Newbie friendliness 48/100

NVIDIA-NeMo/Anonymizer#201 · Opened Jun 30, 2026
feat: Allow for deterministic substituting of PII detected entities Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 42/100

NVIDIA-NeMo/Anonymizer#185 · Opened Jun 9, 2026
feat: add a deny-list for entities in NA Open

task

NVIDIA-NeMo/Anonymizer#164 · 1 assignee · Opened May 19, 2026
feat(rewrite): cost-aware and convergence-aware repair loop Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 38/100

NVIDIA-NeMo/Anonymizer#146 · Opened May 6, 2026
Add entity sensitivity guidance Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA-NeMo/Anonymizer#145 · Opened May 5, 2026
"X and Y" names are getting tagged as a single entity Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 52/100

NVIDIA-NeMo/Anonymizer#142 · Opened Apr 29, 2026
Optimize chunked validation by budgeting per-call token load instead of fixed entity count Open

task

Difficulty 5/5 Over a week Newbie friendliness 45/100

NVIDIA-NeMo/Anonymizer#134 · Opened Apr 23, 2026
Add configurable validator system prompt (replace None default) Open

Difficulty 4/5 3-5 days Newbie friendliness 65/100

NVIDIA-NeMo/Anonymizer#127 · Opened Apr 21, 2026
feat(rewrite): Add another LLM detection step to augment entities Open

enhancement medium priority

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA-NeMo/Anonymizer#118 · Opened Apr 13, 2026
refactor: audit and restructure DEFAULT_ENTITY_LABELS — separate content from structural entities Open

enhancement

Difficulty 5/5 Over a week Newbie friendliness 32/100

NVIDIA-NeMo/Anonymizer#112 · Opened Apr 9, 2026
feat: quick experimentation harness for testing configs and prompts Open

enhancement medium priority

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA-NeMo/Anonymizer#111 · Opened Apr 9, 2026
feat(rewrite): revisit HIGH sensitivity classification and any_high_leaked trigger for needs_human_review Open

enhancement high priority

Difficulty 5/5 Over a week Newbie friendliness 30/100

NVIDIA-NeMo/Anonymizer#107 · 1 comment · Opened Apr 9, 2026
feat: improve visualization in CLI Open

enhancement

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA-NeMo/Anonymizer#105 · Opened Apr 8, 2026
feat(qa): tune quality QA generation and compare prompts Open

medium priority task

Difficulty 4/5 3-5 days Newbie friendliness 52/100

NVIDIA-NeMo/Anonymizer#73 · 1 comment · Opened Mar 28, 2026
feat(detection): domain-aware entity labels via early domain classification Open

enhancement medium priority

Difficulty 5/5 Over a week Newbie friendliness 45/100

NVIDIA-NeMo/Anonymizer#71 · Opened Mar 28, 2026
chore: resolve ty type checker diagnostics (41 errors) Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA-NeMo/Anonymizer#53 · Opened Mar 17, 2026
feat: add domain-aware hyphen handling for partial-token detection (maybe after rewrite integration) Open

enhancement medium priority

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA-NeMo/Anonymizer#46 · Opened Mar 16, 2026
feat: move prompts to versioned template files Open

task

Difficulty 3/5 1-2 days Newbie friendliness 48/100

NVIDIA-NeMo/Anonymizer#9 · Opened Feb 25, 2026
feat: add json and jsonl input format support Open

enhancement

Difficulty 2/5 1-3 hours Newbie friendliness 75/100

NVIDIA-NeMo/Anonymizer#6 · Opened Feb 25, 2026

NVIDIA-NeMo/Anonymizer

Get new issues in your inbox