arcjet-js
Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop
What is arcjet-js?
Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code.
Overview of arcjet-js
What it is
Arcjet is a runtime security platform that ships in your AI code. It detects prompt injection, authorizes agent tool calls, redacts sensitive data, and blocks bots and abuse. These are real-time security building blocks you call inside your app before an action happens.
Key features
- Rate Limiting — token bucket, fixed window, sliding window - Prompt Injection Detection — block attacks before they reach your LLM - Sensitive Information Detection — block PII, credit cards, custom patterns - Bot Protection — stop scrapers, credential stuffers, AI crawlers - Shield WAF — protect against SQL injection, XSS, OWASP Top 10 - Email Validation — block disposable, invalid, undeliverable addresses - IP Analysis — geolocation, ASN, VPN, proxy, Tor, hosting detection
Use cases
Arcjet protects two types of entry points: HTTP route handlers, API endpoints, and middleware (request protection), and AI agent tool calls, MCP server handlers, queue workers, and background jobs (guard protection). It is used to enforce security on each action in real time and audit what happened.
Getting started
npx @arcjet/cli auth login npx @tanstack/intent@latest install npm i @arcjet/next
License and pricing
Licensed under Apache-2.0. Open source.
Based on the project's public README and repository metadata.