Show HN: ModelFuzz – Open-source runtime guardrails for AI agents

Source: Modelfuzz.com· higagan· July 26, 2026

ModelFuzz secures LLM agents against prompt injection. Scan for vulnerabilities, then block unsafe tool calls at the execution layer with one decorator.

This story was reported by Modelfuzz.com. Read the full original article:

Read on Modelfuzz.com

More in Developer & Tools

View all

hol-guard 2.2.0a37

Open-source antivirus and runtime protection for AI agents, tools, MCP servers, plugins, skills, and package installs.

Pypi.org · Jul 26, 2026

whisper-local 0.16.1

Free, open-source, fully offline AI dictation for Windows and macOS. Hold a hotkey, speak, get text at the cursor. 100% local. Powered by Whisper.

Pypi.org · Jul 26, 2026

remedy-ai 0.15.7

Self-improving multi-channel software coding agent framework (memory, learning, tools) — not a medical product

Pypi.org · Jul 26, 2026

caraer-cli added to PyPI

Developer CLI for Caraer apps, webhooks, and serverless functions.

Pypi.org · Jul 26, 2026