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.
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 destroyon 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.What Polaxis does
7-layer firewall on every tool call:- Regex scan — pattern matching, <1ms
- Risk scorer — threat level 0–100
- LLM gate — semantic analysis, fires only when needed
- Behavioral baseline — anomaly detection
- Session graph — cross-call correlation
- Threat intel — known attack patterns
- Policy engine — your custom rules
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 |