LLM Guardrails, Security and Sandboxes

Nox is a security scanner for developers building LLM applications, RAG systems and agents with tool access. It traces untrusted input into model calls and model output into dangerous operations, including paths across functions and files.

OpenSandbox gives developers isolated environments for AI agents that need to execute code or interact with browsers and developer tools. It runs on your own infrastructure, locally with Docker or on a Kubernetes cluster.

CubeSandbox is a self-hosted sandbox service for teams that need AI agents to execute code on their own infrastructure. Each sandbox has its own operating system kernel inside a hardware-isolated MicroVM.

AgentScope is a Python framework for developers building AI agent applications on their own servers. It includes an SDK, a FastAPI backend and a web UI for applications with multiple users and separate sessions.

BeeAI Framework is for developers building AI agents and systems where several agents work together. It lets developers enforce rules on agent behavior while retaining the model's ability to reason.

AgentENV runs isolated environments for AI agents across your own servers. It's for teams building parallel agent workflows or reinforcement learning systems that need many separate sandboxes.

Promptfoo is an open source CLI and library for developers and security teams evaluating AI applications on their own machine. It supports local models through Ollama alongside cloud providers. Evaluations run locally, but tests against cloud models send requests to those providers, and most require an API key.

RedAmon is an AI penetration testing framework for security teams testing systems they're authorized to assess. It connects attack-surface discovery, exploit testing and code fixes in one self-hosted workspace.

MartinLoop runs around coding agents to keep software jobs within agreed boundaries and check their results. It's for developers and engineering teams who want to delegate longer tasks while retaining limits, recovery information and a record of what happened.

APIPark is an AI gateway and API developer portal for teams managing model services and business APIs. It gives applications a common request format and lets teams share APIs with controlled access.

DeepTeam is a Python framework that runs on your machine to test chatbots, AI agents and retrieval-augmented generation applications for security failures. It's for developers and security teams who want adversarial tests they can repeat as an application changes. Its model-powered attacks and scoring use the selected provider; calls to OpenAI or other cloud services send data off your machine.

Omit Redact is beta software for offline PII redaction on Windows 10 and 11, built for people preparing sensitive files to share in legal, healthcare, financial and public sector work. Local language models detect names, organisations and places in seven languages, alongside pattern checks for IDs and account numbers. Files and processing stay on your device, with no account, cloud service or telemetry.

LLM Sandbox is a Python library for developers whose AI agents or applications need to execute generated code. It puts execution in containers on infrastructure you control, with support for local deployments and Kubernetes clusters.

nono is a security runtime for people running terminal AI agents on their own machines or servers. It uses operating system boundaries to restrict an agent's access to files, network services and credentials.

AgentField is a self-hosted AI agent platform for developers building services that need to coordinate tasks under shared access rules. It combines execution, identity and audit records in infrastructure you control.

Reverify helps developers and reverse engineers check AI-generated claims against actual binary files and code behavior. It returns verified, refuted or inconclusive verdicts with evidence, so an assistant's proposed explanation can be checked before you rely on it.

Zerobox is a local process sandbox for developers running AI agents, generated code, builds or tests with restricted access to their machine. It builds on OpenAI Codex's sandbox runtime and can contain a whole agent or individual tool calls.

Agentic Security is an LLM vulnerability scanner for developers, researchers and security teams testing AI models and agent workflows. It probes how systems respond to hostile inputs and attempts to bypass their safety controls.

LLMux is a self-hosted AI gateway for developers who want to use local models and cloud providers through one interface while controlling where requests go. It blocks remote inference by default and logs permitted calls that leave the machine.

Torrix is a self-hosted LLM monitoring tool for teams investigating AI spending and failed requests. It keeps request records in your infrastructure and brings usage analytics and individual traces into one dashboard.

Llama Guard is a family of AI content moderation models for developers who need to check what users submit to an LLM and what the model returns. It supports text and image checks for applications that accept more than written prompts.

claudectl manages multiple Claude Code sessions for developers who need to track parallel work and intervene when an agent gets stuck. Its terminal dashboard brings session activity, approvals and spending into one view.

LLM Guard is a Python security toolkit developers can deploy as a self-hosted API to check prompts and model responses in their applications. It provides screening and sanitization rather than running the application's LLM. The project is archived and no longer maintained, including its associated Hugging Face models.