Каталог
Обзор маркетплейса
CategoryAll Cybersecurity Coding Finance Agentic capability Marketing Orchestration Data & ETL Research Vision & Image Audio & Speech Language & NLP DevOps & Infra Robotics & Control Healthcare Legal & Compliance Gaming & Simulation
9 results
⛨Ограничитель
Presidio — PII Detection & Anonymization
Microsoft's open-source PII detection and anonymization engine supporting 50+ entity types across text, images, and structured data.
ai-supply
↓ 198k★ 4.8
⛨Ограничитель
LLM Guard — Input/Output Security Toolkit
MIT-licensed security toolkit by ProtectAI that sanitizes LLM prompts and responses — blocking prompt injection, toxic content, PII leakage, and secrets.
ai-supply
↓ 142k★ 4.8
⛨Ограничитель
NeMo Guardrails — Programmable LLM Safety Rails
NVIDIA's open-source toolkit for adding programmable safety, topical, and quality guardrails to LLM-based conversational systems.
ai-supply
↓ 96k★ 4.6
⛨Ограничитель
Instructor
Structured outputs for LLMs using Pydantic — patches any OpenAI-compatible client to return validated Python objects.
ai-supply
↓ 61k★ 4.7
⛨Ограничитель
Outlines
Guaranteed structured generation from LLMs: enforce JSON, regex, grammar, or Pydantic schemas at the token level.
ai-supply
↓ 52k★ 4.6
⛨Ограничитель
Guardrails AI
Validate, fix, and filter LLM outputs — define structured schemas and safety rules, then automatically retry when outputs fail validation.
ai-supply
↓ 44k★ 4.5
⛨Ограничитель
Rebuff — Prompt Injection Detector
ProtectAI's self-hardening prompt-injection detector using a multi-stage defence: heuristics, LLM analysis, and a vector canary database.
ai-supply
↓ 41k★ 4.5
⛨Ограничитель
Agentic Security — LLM Vulnerability Scanner
Red-teaming kit for agentic LLM workflows: 2000+ adversarial probes, RL-crafted injections, CI-ready.
ai-supply
↓ 31k★ 4.6
⛨Ограничитель
ModelScan — ML Model Serialization Scanner
ProtectAI's scanner that detects malicious payloads hidden inside pickle, PyTorch, TF, and Keras model files.
ai-supply
↓ 18k★ 4.5