Loading...
Loading...
Safelabs Eval: Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy. 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 Safelabs Eval. This is an automatic list. We have not written a researched verdict for Safelabs Eval 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.
Self-paced bootcamp on Generative AI.
MLExpert is an online AI engineering academy that teaches developers to build AI systems they can show are working, not just demos. The curriculum is hands on and project based: learners start with engineering foundations and a local LLM chatbot with memory, then build a RAG system with citations, produce evaluation re...
Memory that AI Agents Love!
Memanto is a companion memory agent that gives AI coding agents persistent, long term memory. It curates key insights, consolidates context across sessions and briefs an agent the moment it starts, so earlier decisions and preferences are not lost between sessions. It installs with pip and is operated through a comman...
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...
Stop AI agents from doing things they shouldn't.
Permit0 is an open source action authorization layer for AI agents. It sits between what an agent decides to do and what actually executes, applying deterministic policy to every tool call before it runs. A decorator wraps a function, such as a payment refund, and Permit0 scores the call, then allows it, blocks it or e...
Self-hosted runtime control plane for AI agents.
Prismor is an AI agent security control plane. It sits between coding agents and the actions they take, intercepting every tool call, enforcing security policies and keeping a full audit trail. It is built for enterprises that need to control the identity, access and runtime actions of agents such as Claude Code, Curso...
Centralized agent control plane for governing runtime agent behavior at scale.
Agent Control is an open source control plane for governing AI agents at run time. Instead of hard coding guardrails into each agent, teams define centralized policies once and enforce them at every step of an agent workflow, validating LLM outputs and tool calls and updating the rules without taking agents offline. I...