← 최신 프로덕트

Shieldstral

Define safety at runtime for text and images. Shieldstral is a 3B open-weight multimodal guardrail from Mistral.

mistral.ai 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Retroguard

    retroguard.ai

    Verifiably secure AI guardrails

    Hacker News6점

  2. Voxtral

    mistral.ai

    Frontier open source speech understanding models

    Product Hunt추천 194

  3. Warestack

    warestack.com

    Agentic guardrails for safe releases

    Product Hunt추천 428

  4. Voxtral TTS by Mistral AI

    mistral.ai

    Multilingual TTS model with realistic and expressive speech

    Product Hunt추천 156

  5. AI Coding Agent Guardrails enforced at runtime

    sigmashake.com

    Generative AI agent guardrails mapped to MITRE ATLAS AML.M0020: deterministic ALLOW, DENY, ASK, FORCE at the tool-call boundary. Honest-agent. Not a sandbox.

    Hacker News5점