Salus
Guardrails to validate your agent's actions before they execute
Y CombinatorWinter 2026ActiveB2BInfrastructureDeveloper ToolsB2BAPIInfrastructure
What they do
Problem
AI agents can execute incorrect or unsafe actions in real time, causing costly mistakes before teams notice.
Solution
An API that wraps AI agents to validate and potentially block actions at runtime while providing immediate feedback for retries.
Who it's for
Developers and companies building and operating AI agents in production.
Founders
Vedant Singh
Founder
Building to validate your AI agent's actions before they execute AI researcher and formerly @Stanford CS
Open roles 1
Founding GTM / BDR — AI Agent Infrastructure
Company timeline
- Founded2026
- YC batchWinter 2026
- StatusActive
- Team size2 people
- LocationSan Francisco, CA, USA
Similar startups
LiquidMetal AI
LiquidMetal AILiquidMetal AI (fka Seaplane) builds your AI infused ap…
Deasy Labs
Metadata for GenAI workflows
Playgent
Sandboxes for AI agents
DataSuite
Dataset Management for AI Trainers
Coval
Simulation & Evaluation that scales voice and chat AI agents
Halluminate
Data and RL environments to automate knowledge work