Results for agent-guard

Autonomous AI cost protection that actually works. Real-time budget enforcement with auto-kill prevents runaway LLM costs before they happen. Unlike monitoring tools, AgentGuard stops the bleeding.

Express middleware for AI gateway rate limiting, budget tracking, and agent guard.

Framework-agnostic rate limiting, budget tracking, and agent guard for AI gateways.

Don't let orphaned packages clutter your agent. Guard against unregistered pi packages.

Agent Guard — run AI agents without fear. Installs @red-codes/agentguard.

Automatic prompt-injection screening for OpenCLAW tool calls. Auto-registers a before_tool_call hook that screens web fetch/search results and other untrusted tool content.

Self-healing documentation system for AI-assisted development. Prevents doc drift across commits, pushes, and weekly audits.

MCP server that detects and prevents infinite agent loops — circuit breakers, pattern detection, and stuck-agent recovery for agentic systems

Turn a function into an `http.Agent` instance

Netease Yidun Agent Guard - AI Agent security scanning, risk management and runtime protection

A TypeScript SSRF protection library for Node.js (express/axios) with advanced policies, DNS rebinding detection and cloud metadata protection.

Get a user agent string across all JavaScript Runtime Environments

[](https://www.npmjs.com/package/@aws-sdk/middleware-user-agent) [](https://www.npmjs.c

An HTTP(s) proxy `http.Agent` implementation for HTTP

[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-browser) [](https://www.n

Maps proxy protocols to `http.Agent` implementations

An HTTP(s) proxy `http.Agent` implementation for HTTPS

[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-node) [](https://www.npmjs.com/

HTTP proxy tunneling agent. Formerly part of mikeal/request, now a standalone module.

Library to bypass DDoS Guard protection (https://ddos-guard.net/en) using Node and Axios.

Loads environment variables from .env file

the http/https agent used by the npm cli

Global HTTP/HTTPS proxy configurable using environment variables.

Lightweight security guardrails for tool-enabled agent runtimes: scan risky payloads, redact secrets, expose stdio/HTTP MCP tools, and write audit logs.