List your company

Salus runtime

AI safety and governance · by Salus

A policy-aware proxy and reasoning engine that sits between every agent and every tool, reasoning against policies, evidence, prior actions, and context to produce structured verdicts on proposed actions before they touch backend systems.

Visit website

Where it ranks

Current edition · updated Oct 20, 2026

What it does

A policy-aware proxy and reasoning engine that sits between every agent and every tool, reasoning against policies, evidence, prior actions, and context to produce structured verdicts on proposed actions before they touch backend systems.

  • Agent action safety
  • Policy enforcement on agent tool calls
  • Shadow replay of agent sessions
  • Synthetic red-teaming of agent workflows
  • Observability and audit of agent decisions
Category
AI safety and governance
Users
Teams deploying tool-calling AI agents
Public API
Not offered

Not yet disclosed: deployment options, platforms, languages and support channels.

Pricing

  • Subscription$500/month

Prices as published by Salus, checked Oct 2026.

Security and compliance

As reported by Salus. Ask for audit reports before you buy.

  • Field-level redaction (hash, drop, or mask argument fields before reaching Salus)
  • Customer data not used for model training
  • Decision events retained 90 days by default; exportable
  • Imported logs deletable on request or via dashboard
  • Security review process: company responds to questionnaires within one business day

Reviews

No reviews yet

Reviews come from people who use Salus runtime at work. Share how your team uses it to help other buyers decide.

Write a review

Alternatives

See the full ranking

  • Clawvisor Gateway

    by Clawvisor

    A security gateway that intercepts AI agent requests to verify task intent, scope tool access per task, and log actions with fail-closed containment.

    #1 in Enforce AI guardrails

  • Protoguard

    by Metorial

    Metorial's security layer for AI agents.

    #2 in Enforce AI guardrails

  • Stacktrace Personal Agent Gateway

    by Stacktrace

    A gateway for personal agents used by customers that verifies each agent, holds risky actions for customer approval, and records masked session decisions.

    #4 in Enforce AI guardrails

  • Silmaril Firewall

    by Silmaril Security Inc

    AI application firewall that evaluates intent, context, tool calls, and execution state to block harmful outcomes in agent systems.

    #5 in Enforce AI guardrails

  • Responsible AI Guardrails

    by Airia

    Secure every prompt, response, and workflow interaction with real-time protections that prevent data exposure, block manipulation, and enforce enterprise standards.

    #6 in Enforce AI guardrails

  • Bifrost Edge

    by Maxim AI

    Edge deployment variant of Bifrost.

    #7 in Enforce AI guardrails

Is this your product?

Claim it to keep details accurate and submit evidence for the next ranking review.

Claim Salus runtime