Skip to main content
Salus

Salus: AI Security

Founded 2026|San Francisco, CA|2-10 people|Unknown

Respan Gateway: up to 55% off tokens on Gemini, GPT, Claude and 1,000+ more models. One API key, 0% fee.

What is Salus?

Key features

Core capabilities this platform advertises.

  • Runtime action validation
  • Policy-based guardrails
  • Pre-execution blocking
  • Structured feedback for self-correction
  • Agent action auditing

Strengths and tradeoffs

What this tool does well, and the limitations to keep in mind.

Pros

  • Solves a critical problem — agents executing incorrect actions can cost enterprises thousands per incident
  • Clean developer experience with Python SDK, decorator-based instrumentation, and framework-agnostic compatibility
  • 58% self-recovery rate on blocked actions means agents keep working rather than failing hard
  • Comprehensive approach combining runtime guardrails, observability, and pre-deployment adversarial evals
  • Well-funded at .7M with strong Stanford CS founding team

Cons

  • No public pricing creates friction for developer adoption in a space with transparent free tiers
  • Very early stage (founded 2026) with a small team and limited enterprise track record
  • Competes with Guardrails AI and built-in safety features from OpenAI and Anthropic
  • Adding a validation layer introduces latency to every agent action

Plans & pricing

What's included in each plan, and how the tiers compare.

SDK

Free

 

  • Open SDK (pip install salus-ai)
  • Basic guardrails
  • Python integration

Platform

Contact for pricing

 

  • Full runtime validation
  • Observability dashboard
  • Adversarial evals
  • PII detection
  • Human-in-the-loop
View official pricing page

Common use cases

Teams deploying AI agents that take real-world actions

  • Agent safety enforcement
  • Action policy compliance
  • Runtime guardrails
  • Agent audit trails

Using Salus with Respan

Salus validates agent actions before execution, while Respan monitors the LLM calls driving those actions. Together they provide both proactive safety (blocking bad actions) and reactive observability (tracking performance and costs).

  • Block incorrect agent actions with Salus while monitoring LLM performance via Respan
  • Correlate Salus action blocks with Respan traces to identify problematic prompt patterns
  • Combine Salus runtime guardrails with Respan cost tracking for safe and cost-effective agent operations

Run Salus in production with Respan

Up to 55%Off tokens
1,000+Models
0%Fee

Respan lets you trace LLM and agent calls across any model or framework, A/B test prompts on production traffic, and route requests across 1,000+ models through one gateway.

Best Salus alternatives & competitors

Top companies in AI Security you can use instead of Salus.

Compare Salus

Side-by-side comparisons with other tools in this category.

Best integrations for Salus

Companies from adjacent layers in the AI stack that work well with Salus.

Last verified: March 27, 2026