Salus

Active

Guardrails to validate your agent's actions before they execute

Winter 2026Founded 20262 peopleSan Francisco, CA, USA

www.usesalus.ai/ ↗LinkedIn ↗

Generate ideas →

AI insightcan contain mistakes

Agent Action GuardrailsAPI/InfraAI companies, agent developers, platformsLow competition

Moat

Real-time action validation prevents costly errors; blocks mistakes before execution; early adoption in agent ecosystem.

Key risk

Market nascent; competing solutions may arise; building block that larger platforms may consolidate.

Why now

Agent adoption scaling; high-stakes failures (refunds, data corruption) drive safety demand.

Competitors

Emerging space, custom guardrails

About

Your agent processed a refund without looking up the order ID, costing you thousands. You only found out three hours later from a support ticket. Evals, output scoring, and observability can reduce the likelihood of mistakes like these occurring - but there's no solution that inspects and prevents an action as it’s about to execute. Salus does that. We’ve built an API that wraps around your agent and checks its actions at run time, blocking incorrect ones and providing immediate feedback to guide retries. Kevin and Vedant were roommates at Stanford, where they both studied computer science.