> ## Documentation Index
> Fetch the complete documentation index at: https://docs.polaxis.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Polaxis — AI Agent Security & Governance Platform

> Polaxis is the runtime security and governance layer for AI agents. Intercepts every tool call, blocks threats, enforces policies, and generates SOC 2 / GDPR / OWASP compliance reports.

# Introduction

**Polaxis** is the security and governance layer for AI agents.

It sits between your agents and every tool they call — intercepting, evaluating, and blocking dangerous actions before they execute.

## The problem

AI agents are shipping to production without guardrails. When something goes wrong — and it does — there's no audit trail, no kill switch, no way to explain what happened.

* **April 2026:** An AI agent deleted an entire production database in 9 seconds via Railway API
* **December 2025:** Claude Code ran `terraform destroy` on 1.9 million rows
* **2025:** 28.65 million secrets exposed on GitHub — AI-related leaks up 81%

## The solution

One SDK. Three lines. Every tool call governed.

```python theme={null}
from polaxis import Polaxis

guard = Polaxis(api_key="ag_prod_...", agent_id="billing-agent")
result = await guard.evaluate(tool_name, tool_input)
# → allow | block (raises BlockedError) | escalate (waits for human)
```

## What Polaxis does

**7-layer firewall** on every tool call:

1. **Regex scan** — pattern matching, \<1ms
2. **Risk scorer** — threat level 0–100
3. **LLM gate** — semantic analysis, fires only when needed
4. **Behavioral baseline** — anomaly detection
5. **Session graph** — cross-call correlation
6. **Threat intel** — known attack patterns
7. **Policy engine** — your custom rules

**89% of calls never touch an LLM.** Pure Python speed.

## Four pillars

| Pillar                 | What it does                                                               |
| ---------------------- | -------------------------------------------------------------------------- |
| **Policy Engine**      | YAML rules that block, allow, or escalate any tool call                    |
| **Human Approvals**    | Slack notifications for high-risk actions — one click to approve or reject |
| **Budget Controls**    | Session and daily spend caps. Hard stop when limit hit.                    |
| **Compliance Reports** | SOC 2, GDPR, HIPAA, EU AI Act, OWASP — one-click PDF                       |

## Key stats

* **\<1ms** policy decision latency
* **Sub-50ms** full firewall
* **89%** of calls evaluated in pure Python (no LLM cost)
* **5 frameworks** covered in one compliance report

## Pricing

| Plan       | Price       | Evaluations     | Agents    |
| ---------- | ----------- | --------------- | --------- |
| Free       | \$0         | 10,000/month    | 1         |
| Pro        | \$149/month | 500,000/month   | Unlimited |
| Scale      | \$499/month | 5,000,000/month | Unlimited |
| Enterprise | Custom      | Unlimited       | Unlimited |

[Start for free →](https://polaxis.io)