ai-agentguard is an open-source CLI tool that monitors AI coding agents for security threats such as remote code execution, MCP poisoning, and API key theft. It is designed for developers working with AI agent frameworks to enhance security.
ai-agentguard sits in PulseGate's Other AI category. It focuses on detecting and preventing security threats in AI coding agents before execution. It is built as an open-source project for developers building or deploying AI coding agents. ai-agentguard is open source under the Apache-2.0 license. It runs on the web and the command line.
jeromwolf builds and maintains ai-agentguard, and it first shipped in 2026. The project is developed in the open on GitHub with 6 commits in the last 90 days. Among its 5 catalogued features are security monitoring, RCE detection, and MCP poisoning detection. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do