# Kastra

> For security teams: Kastra enforces runtime authorization on AI agents with sub-1ms latency so you prevent unauthorized tool use and prompt injection before incidents.

Source: https://tools.launchllama.co/products/kastra
Markdown: https://tools.launchllama.co/products/kastra.md
Generated: 2026-11-04T17:17:08.171Z

## Facts

- **Name:** Kastra
- **Short description:** For security teams: Kastra enforces runtime authorization on AI agents with sub-1ms latency so you prevent unauthorized tool use and prompt injection before incidents.
- **Website:** https://kastra.ai/
- **Categories:** Developer Tools, Artificial Intelligence, GitHub
- **Listing type:** product_hunt
- **Upvotes on Launch Llama:** 398
- **Listed since:** 2026-07-28
- **Featured (paid) listing:** no

## Full description

Kastra is the runtime authorization layer for AI agents. It decides what agents can and cannot do before actions execute, enforcing policies with sub-1 ms latency across tools, prompts, inputs, and outputs. Use one control plane to govern agents and policies across Claude Code, Cursor, Codex, OpenClaw, the Anthropic SDK, the OpenAI SDK, and more. Prevent unauthorized tool use, prompt injection, and exposure of sensitive data before they become incidents. Trust the rules, not the agents.

## Notes for agents

- Generated on request from live Launch Llama data, so it is always current.
- Human page: https://tools.launchllama.co/products/kastra
- Site overview: https://tools.launchllama.co/llms.txt (long form: https://tools.launchllama.co/llms-full.txt)
- Every listing as markdown: https://tools.launchllama.co/catalog.md
- Search the catalog over MCP (https://tools.launchllama.co/mcp) or REST: https://tools.launchllama.co/developers