# Kastra

Runtime authorization layer that approves or blocks AI agent actions before execution.

- Category: Developer Tools
- Pricing: Free plan available
- Tags: Security, Cybersecurity
- Website: https://kastra.ai/?via=aigregator
- Aigregator page: https://aigregator.com/tools/kastra
- API: https://x402.aigregator.com/v1/tools/kastra

## Overview
Kastra sits between AI agents and the actions they try to take, prompts, tool calls, shell commands, API requests, and checks each one against a defined policy in under a millisecond before it's allowed to run. The pitch is that most AI safety tooling monitors what already happened; Kastra is meant to decide what's allowed to happen at all, using a typed, versioned policy-as-code language rather than ad hoc rules.

A component called Kastra Edge governs coding agents like Claude Code, Cursor, and Codex CLI directly on a developer's laptop, while an OpenClaw integration extends the same policy checks to browser agents performing clicks, form fills, and navigation. Every decision is written to a signed, append-only audit log that can stream to SIEM tools like Datadog, Splunk, or S3, and a "Recon" feature retroactively scans an AI system's history to flag risky past actions and draft policies automatically.

Kastra deploys to the cloud, self-hosted, or air-gapped environments, with SDKs for TypeScript, Python, Go, Rust, Java, and Swift. Kastra Labs Inc. holds SOC 2 Type II certification and is pursuing ISO 27001, targeting regulated sectors like finance, healthcare, and the public sector, alongside a free tier for solo developers. As infrastructure aimed at teams already running production AI agents, it isn't relevant to someone just experimenting with a single chatbot.
## Key Features
- Sub-millisecond runtime policy checks
- Policy-as-code language
- Signed append-only audit trail
- SIEM integrations
- Retroactive risk scanning (Kastra Recon)

## Use Cases
- Blocking unauthorized shell commands from coding agents
- Auditing every action an AI agent takes for compliance
- Governing browser agent actions before they execute

## Pricing Plans
- Free: Free
- Pro: $19.99/month
- Team: $49.99/month
- Enterprise: $-1/month

## Alternatives
- [Lakera](https://aigregator.com/tools/lakera)

---
Source: Aigregator — AI tools directory. https://aigregator.com/tools/kastra