Shieldstral

Define safety at runtime for text and images

Product HuntOpen SourceLaunched Aug 6, 2026105#10 of the day

About Shieldstral

Shieldstral is a 3B open-weight multimodal guardrail from Mistral. Define safety policies in natural language at inference time. It evaluates text, images, or both from a single token output, running locally on a single 16GB GPU.

The person behind Shieldstral

Arthur Mensch
Maker
Co-founder and CEO @Mistral AI.
Email not found yet

Shieldstral's team page →

More Open Source launches

Inyon
Answer your coding agents from your phone
Oct 23, 2026 · 1 person
Nanotype
A private online text editor with markdown. Open and type.
Oct 23, 2026 · 1 person
Whiteboard
the open-source IDE for thoughtful software design
Oct 22, 2026 · 1 person
Tetriz Engg Intelligence + Connectors
Connect coding sessions to PRs, issues, quality, and ROI
Oct 22, 2026 · 1 person
Tessary
Stop your agents from failing silently in production
Oct 22, 2026 · 1 person
LLM Test Server
Your LLM tests, without the provider
Oct 22, 2026 · 1 person

Made Shieldstral? Ask us to remove this listing or your details.