Salus
Salus is a YC Winter 2026 (W26) company. Based in San Francisco, CA, USA. Team of 2.
About Salus
Summary
Salus builds a runtime authorization layer for AI agents, sitting between an agent and the systems it acts on. Before any action executes, Salus checks it against policy, live evidence, and intent, blocks ones that fail, and returns the exact correction the agent needs to retry. It replaces the gap left by evals and observability tools, which can flag mistakes only after they have already happened.
Business model
API sold to developers building or operating AI agents
Go-to-market
Developer teams building AI agents in production adopt Salus by wrapping their agent through the API, with a self-serve path via documentation and a get-started flow on the website.
From the Y Combinator listing
Guardrails to validate your agent's actions before they execute
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.
Facts
- B2B / B2B -> Infrastructure
- San Francisco, CA, USA
- 2
- Active
- Early
Founders (2)
- Kevin Pan
Score every batch against your own thesis
GPAgent's sourcing agent reads every company in a batch, scores each one against your fund's thesis in a private workspace, and lines up the founders worth meeting before Demo Day. You decide who to contact. Your scores, notes, and pipeline never appear on these pages.
How Accelerator intelligence works