Hacker News AI· VDudaG-A·· 2 hr agoAI score70
Show HN: Agent Guard – limit what an AI agent can do when it gets tricked
Show HN: Agent Guard – limit what an AI agent can do when it gets tricked
AI summary
Agent Guard is a TypeScript library for Node.js 22+ that decides which tool calls an AI agent may make, checking each call against registered tools, task grants, tenant and recipient limits, per-action human approvals, and budgets. It assumes the agent can be misled and limits the effect rather than detecting prompt injection, and it does not cover actions taken outside the guard or sandbox tool handlers by default. Version 1.3.1 is Apache-2.0 licensed, with adapters for Claude, OpenAI, Gemini, Bedrock, the Vercel AI SDK, the OpenAI Agents SDK, LangChain and MCP clients.
Source: Hacker News AI · github.com