#134 · Primary category: Cybersecurity & Decryption Tools

arcjet-js

agent-security ai-agents ai-security application-security bot-detection llm-security mcp pii-detection prompt-injection-detection rate-limiter runtime-security tool-authorization typescipt

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.

Project last updated:08/28/26

GitHub Stars

681

Forks

32

Contributors

17

License

Apache-2.0

Why we included this project

AI features that take real actions, like calling tools, reading data, or hitting external APIs, carry risks that ordinary web security doesn't cover. Arcjet is built for that gap. It's a JS/TS SDK that runs inside your application, with runtime building blocks that check each action before it happens: flagging prompt injection attempts, authorizing which tools an agent may call, redacting sensitive data before it leaves your system, and adding bot detection and rate limiting. The packages split into request protection for HTTP routes and middleware, and guard protection for agent tool calls, MCP server handlers, and background jobs, so one policy can cover both entry points. If you're shipping an agent, an MCP server, or an AI feature that touches user data, this is a practical way to enforce guardrails and keep an audit trail without standing up a separate proxy.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category