Salus
ActiveAI-nativeGuardrails to validate your agent's actions before they execute
What it does
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.
Its site says now · captured 2026-08-23
Salus — Runtime control for AI agent actions
Salus checks each AI agent action against policy and evidence before it reaches your systems, then helps the agent correct unsafe actions.
Next to it in Agent infrastructure · Agent action validation and guardrails
- AshrY Combinator W26
Automated Multi-Modal Testing for Agents
- Klaus AIY Combinator W26
Fast and Safe OpenClaw on the cloud
- SpongeY Combinator W26
Financial infrastructure for the agent economy
- PolymathY Combinator W26
Simulation environments to train & evaluate long-horizon AI agents
- Ressl AIY Combinator W26
Train, eval and build autonomous agents
- SentrialY Combinator W26
Datadog for Agent Reliability
- SkillsyncY Combinator W26
Move context across agents and teammates
- MavenY Combinator W26
Payments Infrastructure for Voice Agents