Loading...
Loading...
Hoop: Open-source enforcement at runtime that masks sensitive data and blocks destructive commands from AI agents. 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 Hoop. This is an automatic list. We have not written a researched verdict for Hoop 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.
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...
The open-source TypeScript SDK for running AI coding agents in sandboxes.
AgentBox is an open source TypeScript SDK from Twill for running AI coding agents inside sandboxes through one unified API. Instead of calling an agent command line tool in non interactive mode, it launches each agent as a server process inside the sandbox and talks to it over WebSocket or HTTP, which preserves approva...
Get AI to teach and answer questions for you - just by typing!
This platform is an open source AI teaching agent that turns an instructor's material into one on one tutoring. A creator supplies expertise and teaching intent once, as a lesson framework or syllabus, and the system expands it into complete lessons, activities and assessments, then adapts explanations, tone and pacing...
An Omni Real-Time Assistant for Everyone
AlphaAvatar is an open source, self hostable runtime for a real time personal AI assistant that can talk, see, remember, plan and act. It focuses on the personal assistant layer: real time voice and vision interaction, persistent user context, and an optional real time virtual avatar, connected to tools and long runnin...
The RL Bridge for LLM-based Agent Applications.
AReaL is open source reinforcement learning infrastructure for training large language models and the agents built on them. It connects foundation model training with agent based applications, so teams can post train models on agentic tasks such as multi turn tool use and long horizon reasoning with reinforcement learn...
Autolith is a self-modifiable general purpose Lisp AI agent
Autolith is an open source terminal programming agent written in Common Lisp that can inspect and rewrite its own implementation while it runs. The whole agent lives in one live Lisp image, and it uses Common Lisp features such as describe, conditions, restarts, CLOS protocols and runtime source forms to examine and ch...