Loading...
Loading...
Emilia Protocol: Authority control plane for autonomous work. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Emilia Protocol. This is an automatic list. We have not written a researched verdict for Emilia Protocol yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
IAM for your AI agents.
node9 is an access control layer for AI agents. It sits in front of every tool call an agent makes and decides whether to allow it, hold it for human review, or block it, with every decision recorded in an audit log. It works with Claude Code, Codex, Cursor, Copilot CLI and other agents, and the vendor states that it g...
Security toolkit for AI agents.
AgentSeal is a security scanner for AI agents that red teams system prompts, audits Model Context Protocol servers and inspects skill and instruction files from a single command line tool. It installs from PyPI or npm and runs four core commands: scan, which fires an adversarial probe suite at a prompt; guard, which au...
Build Secure and Compliant AI agents and MCP Servers.
This platform is an AI security and compliance product for enterprises adopting generative AI. It gives security teams visibility into how generative AI tools are used across the organization, including unsanctioned shadow AI, detects data exfiltration risks in real time, and tests AI applications and vendors against g...
Open-source adversarial testing engine, SDK, and CLI for AI agents.
Humanbound is an AI agent security testing platform that can be run as a Python command line tool or through a hosted platform. A user points it at the endpoint of a chatbot or agent, defines a scope or lets the tool extract one, and receives findings mapped to OWASP LLM and agentic AI categories. Tests cover prompt in...
Open-source AI agent firewall for MCP security and agent egress.
Pipelock is an open source agent firewall from PipeLab that sits at the boundary between an AI agent and the outside world. It mediates MCP, HTTP and WebSocket traffic, wraps stdio MCP servers, and can issue signed action receipts that a third party can verify offline when receipt signing is configured. It is written ...
OWASP Foundation web repository
OWASP Agent Memory Guard is an open source runtime defense against memory poisoning in AI agents. Agents that persist memory across sessions treat anything written there as a privileged input on later turns, so an attacker who plants text in the wrong field can override instructions, exfiltrate data or hijack tool call...