A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.
-
Updated
Sep 20, 2026 - Python
A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.
A closed-loop control plane for cloud-native distributed systems: forecast-driven autoscaling, streaming-pipeline recalibration, governed ML model lifecycles, and detection paired with automated recovery. Includes zero-shot multilingual PII redaction at the point of processing.
Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment
AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy.
privacy-first context graph engine for AI agents and human teams.
Real-time PII detection and redaction for AI chat interfaces.
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.
Local-first PII anonymization and de-anonymization in Go. Multilingual via GLiNER NER + 73 pattern recognizers. Self-host runs as a single binary that never leaves your network.
Fast ONNX inference for GLiNER, GLiClass, GLiFormer, and System One — Python API, Rust runtime, CPU/GPU
Collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 40 MCP tools.
Deterministic-first PII/PHI de-identification you can prove: benchmarked recall, jurisdiction policy packs, reversible tokenization, audit trail. CLI + library + GitHub Action; optional GLiNER / Gemma contextual tier.
Comparison case study between Gliner V2 vs OpenAI Privacy filter model for PII Redaction
Benchmark harness and leaderboard for zero-shot, open-type named-entity recognition — GLiNER, GLiNER2, and LLM backends with nervaluate scoring and bootstrap CIs.
Text preprocessing and PII anonymisation for NLP/ML. ONNX NER ensemble, language detection, stopword removal. Built for statistical ML and language models.
60 zero-shot information-extraction & classification systems (57 benchmarked) across 32 families — extractor encoders, zero-shot classifiers, cross-encoder rerankers, typed-decision engines — local, Ollaya-served & hosted (OpenRouter, Cloudflare, TypeSafe); measured accuracy/latency/cost benchmarks, 9-language suite, web UI
威胁情报实体提取平台:NER 实体提取 / MITRE ATT&CK 识别 / 联网情报扩线。Threat Intelligence Entity Extraction: NER, ATT&CK mapping, TI enrichment (FastAPI/Vue3/Docker)
Spoiler-aware knowledge graph for web novels — entities & relationships fenced to the chapter you've read. Local-first, GLiNER floor + optional LLM.
Self-hosted, GDPR-native AI agent for sovereign organisations. Multi-LLM, multi-channel (web, voice, mobile, Telegram), HITL on every irreversible action, native PII anonymisation pipeline. MIT License.
Easily configurable API & frontend providing simple access to dynamic NER models.
To associate your repository with the gliner topic, visit your repo's landing page and select "manage topics."