SDK
Free
- Open SDK (pip install salus-ai)
- Basic guardrails
- Python integration
Respan Gateway: up to 55% off tokens on Gemini, GPT, Claude and 1,000+ more models. One API key, 0% fee.
Salus provides a runtime validation layer for AI agents, intercepting and checking every tool call before it executes. Part of YC W2026, the company was founded by Stanford CS roommates Vedant Singh and Kevin Pan, and has raised .7M in total funding.
The platform wraps around existing agent frameworks (OpenAI, Anthropic, LangChain, LangGraph, CrewAI) and validates proposed actions against an evidence cache of prior tool outputs and conversation history. Users define constraints using YAML, markdown, or plain English. When Salus blocks an incorrect action, it returns structured feedback enabling agents to self-correct — the company reports a 58% successful recovery rate on blocked actions.
Beyond runtime guardrails, Salus includes PII detection, content moderation, budget/loop protection, human-in-the-loop escalation, and an observability layer with real-time streaming of agent interactions. The evals system generates thousands of adversarial test scenarios to measure tool-call accuracy before deployment. Developers instrument their code with a simple Python decorator and define function dependencies.
Core capabilities this platform advertises.
What this tool does well, and the limitations to keep in mind.
Pros
Cons
What's included in each plan, and how the tiers compare.
Free
Contact for pricing
Teams deploying AI agents that take real-world actions
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).
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.
Top companies in AI Security you can use instead of Salus.
Wiz
Protect AI
Snyk
Lakera
Prompt injection detection
HiddenLayer
Descope
Agent identities with per-agent and per-tool scopes
CalypsoAI
Cisco (Robust Intelligence)
AI firewall and guardrails
Prompt Security
Full-stack GenAI security platform
Pangea
Guardrails AI
NeMo Guardrails
Arthur AI
Nightfall AI
Lasso Security
LLM interaction security
Oximy
Shadow AI discovery
Side-by-side comparisons with other tools in this category.
Companies from adjacent layers in the AI stack that work well with Salus.
Last verified: March 27, 2026