PyRank
  • Search
  • PyPI
  • GitHub
  • Insights
  • Compare
  • Advisories
  • Ecosystem
  • About

Gliner Python Packages

Python packages with the GitHub topic gliner. Sorted by monthly downloads, with stars and forks.
rhnfzl
squeakycleantext

Text preprocessing and PII anonymisation for NLP/ML. ONNX NER ensemble, language detection, stopword removal. Built for statistical ML and language models.

950 8 0
ddickmann
vllm-factory

Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment

722 83 10
julianschelb
implicit-word-network

Extract and explore (contextual) implicit entity networks from text corpora

580 0 0
carnaval-ai
carnaval

Reversible PII anonymization for LLM pipelines: mask names, emails and bank details before text reaches a cloud LLM, then restore them in the response. Local-first, encrypted vault, 6 languages. Python, Apache-2.0.

359 1 0
sedoglia
ai-privacy-anonymizer

Uno strumento Python che consente di caricare file di vario formato contenenti dati personali, rilevare e mascherare automaticamente le PII (Personally Identifiable Information), e produrre in output un file anonimizzato con la stessa estensione dell'originale, pronto per essere caricato su chatbot AI senza rischi di data leakage.

254 0 0
Andrew-Chen-Wang
gliner2-mlx

MLX support for gliner2

190 1 2
atliq
guardex-ai

Python SDK for LLM guardrails with safety classification, PII detection, prompt injection defense, and grounding checks. Protect AI applications locally with zero external APIs, streaming support, and plug-and-play integration for any LLM.

175 28 11
brokenbartender
sovereign-vault

Reversible PII tokenization for LLM pipelines — send documents to cloud AI without exposing real data. Part of LexiPro Sovereign OS.

97 0 0
Jhiynn
privaparse

Local privacy layer for LLM traffic: detects PII, swaps it for deterministic placeholders, restores it in the answer. Nothing leaves the machine.

78 0 0
    • Original data from PyPI, GitHub, and OSV; downloads served through ClickHouse
    • Sources & methodology