Tool overview
Salus is listed under AI Governance Safety & Evaluation AI tools.
What is Salus?
Salus sits between an AI agent and its tools to inspect proposed actions before execution. It can allow, clarify, repair, rewrite, escalate, or refuse actions while logging policy evidence and supporting shadow-mode replay before live enforcement.
Best for
Teams deploying agents that can write to consequential systems
Who is it for?
Decision note
Rebuilt from the original export under the complete V412/V411 factual-source-verification workflow. Preview only. Apply remains blocked until Failures = 0, Warnings = 0, Unmapped = 0, Missing = 0; explicit clears are reviewed; image import is disabled or V380 accepts the asset; a representative WordPress edit screen is compared with the export and proposed row; and a post-Apply zero-change Preview succeeds.
Key features
Policy-aware proxy for agent tool actions
Shadow replay before live enforcement
Structured repair, clarification, and escalation
Decision events and evidence-backed audit logs
Use cases
Protect refunds and payments
Validate appointment and CRM updates
Guard messages, claims, and handoffs
Audit high-risk agent actions
Pros
- Starts with one protected tool route
- Works with common agent and voice stacks
- Private deployment options for enterprise
Cons
- Pilot begins at five hundred dollars monthly
- Charges depend on routes and action checks
- Implementation requires backend route changes
Limitations
The paid Pilot is not a free trial or proof of concept.
Policies still require domain review, monitoring, and incident ownership.
Pricing details
Billing options
Pricing note
Pilot starts at $500/month for one protected tool route. Partner starts at $2,500/month for up to ten routes. Enterprise pricing is custom for higher volume, private deployment, security review, and rollout requirements.
Supported languages
- English
Integrations
OpenAI
Anthropic
Gemini
LangChain
LangGraph
CrewAI
LlamaIndex
Retell
Vapi
MCP
Please log in to join the discussion.