LLM Guardrails, Security and Sandboxes

ECC adds reusable engineering workflows to AI coding assistants. It's for developers who want editable plans, test-first development and separate review contexts across sessions.

Cua supplies desktops and automation tools for developers building AI agents that operate native apps and browsers. You bring your own agent and model; Cua provides the computer environment and ways to interact with it.

LangWatch helps AI teams test agent behavior before release and investigate production failures. Teams can reproduce a failed conversation and check how an agent handles it again.

Context Mode is a local MCP plugin for developers whose AI coding agents fill their context windows with logs, file reads and search results. It stores large tool outputs on your machine so the agent can retrieve relevant passages as needed.

Garak is an LLM vulnerability scanner for developers and security teams assessing models or dialogue systems. It attempts to provoke unwanted responses so teams can identify weaknesses in the systems they test.

Higress is an AI gateway for teams building AI apps and agents that need shared controls across model requests and tool calls. It brings model APIs, MCP services and Kubernetes inference workloads behind one entry point.

Future AGI helps teams test AI agents, investigate production failures and compare prompt changes. It brings evaluation and monitoring into the same platform so teams can connect poor responses to the steps that caused them.

Open Multi Agent is a TypeScript framework for developers building self-hosted AI agent teams. It lets you coordinate work across agents, require human decisions before consequential actions, and inspect what happened afterward.

OpenZiti LLM Gateway is a self-hosted API proxy for developers and teams connecting AI applications to inference servers across private networks and cloud services. Its optional zrok integration uses OpenZiti for identity-based access and end-to-end encryption, so clients and backends can connect across network boundaries without opening inbound ports.

LiteLLM is an AI gateway for platform teams managing model access across applications and providers. It puts cloud and self-hosted models behind a shared interface so developers can switch providers without rewriting their integration.

NeMo Guardrails is a Python toolkit for developers building AI assistants that need rules for what they say and which actions they take. It adds checks around conversations, document-based answers and tool use.

Strix is an AI penetration testing tool for developers and security teams assessing code, web applications and APIs. Its free, open source edition runs locally with Docker under the Apache 2.0 license. It supports local models through Ollama or LM Studio, as well as remote providers such as OpenAI and Anthropic; cloud-backed runs send model requests to the selected provider.

AgentArk is a self-hosted AI agent runtime for people who want a personal assistant that remembers preferences and carries out ongoing work under their control. It runs through Docker on macOS, Windows and Linux, with a browser interface for chat, tasks and action review. It's free and open source under Apache 2.0.

Agent Safehouse is a local macOS sandbox for developers who want coding agents to edit a project while limiting their access to unrelated files. The operating system enforces the restrictions, so they don't depend on the agent following written instructions.

Shuru gives AI agents a disposable Linux virtual machine on your Mac. It's for developers who want coding assistants to execute code, install packages and use tools in an environment isolated from the host.

Hypha is a TypeScript AI agent framework for developers building applications that need controlled tool use and recoverable work. It separates an agent's planning and tool choices from the execution layer that decides which actions may proceed.

Kong Gateway gives platform teams a shared place to manage API, LLM and MCP requests. It helps teams apply access and traffic policies across services and AI applications on infrastructure they control.

h5i gives AI agents tools to investigate vulnerabilities in web applications you own or are authorized to test. Teams can review the evidence behind findings and turn confirmed attack flows into security regression checks.

SkillSpector scans AI agent skills before installation or publication. It helps people reviewing Claude Code, Codex CLI, Gemini CLI and MCP skills spot risks in their instructions, permissions and code.

LLM Router is a self-hosted AI gateway for teams connecting applications to local LLM servers and cloud providers. It puts a shared interface in front of your models so clients can use the same gateway across backends.

ASSERT is a local-first Python framework for developers testing AI agents and LLM applications against their own requirements. It turns written expectations into evaluations for quality, safety, and regression testing.

rizzo-pii replaces personal information in Italian legal text with placeholders before you share it with an AI service. It's built for law firms, accountants and notaries who need to work with sensitive documents.

Archestra Community Edition is a self-hosted AI platform for teams managing access to company tools and models. It gives coding assistants, internal agents, and staff chat a shared place to enforce policies and track activity.

RamaLama runs AI models for local chat or a self-hosted REST API. It's for developers who want a container workflow for trying models on their own hardware and serving them in production.

Clawk gives coding agents a disposable Linux VM for installing packages, running builds and starting services locally. It's for developers who want an agent to control its working environment while keeping unshared host files and the host keychain outside the guest.

GoModel is a self-hosted AI gateway for developers and platform teams sharing access to local models and cloud providers. It centralizes provider choice and usage policies behind APIs compatible with OpenAI and Anthropic SDKs.

PyRIT is an open-source Python framework for testing generative AI systems, with a self-hosted CoPyRIT browser interface. Its backend serves the interface locally, and Docker deployment is available. Targets and scorers use configured endpoints, including Ollama or cloud providers. The documented OpenAI configuration sends requests to OpenAI; hosting the testing interface locally does not make every model local.

Plano is a self-hosted AI gateway for developers building applications with multiple agents. It handles shared routing, orchestration and monitoring outside the agents, so developers don't need to build those functions into each one.

Omnigent coordinates AI agents for developers and teams who want to combine coding assistants, control their access, and supervise work in shared sessions. It runs locally or on a self-hosted server, with remote cloud sandboxes as another option.

Coding Tools MCP gives AI chat apps and coding agents access to a repository on your machine. It's for developers who want to use an existing MCP client to inspect code, make edits and check a running project.

PanGuard AI checks skills and MCP servers for threats before AI agents load them, then watches their actions at runtime. It's for developers and teams who want protection against prompt injection, poisoned tools and malicious skills.

Guardrails AI is an open-source Python validation framework that runs inside your application or as a self-hosted service. It's for developers who need to check LLM inputs and responses before their apps use them. It provides a validation layer around model interactions; it doesn't supply local model inference.

Quicksand gives AI agents a Linux virtual machine for executing code and working with desktop apps on your own hardware. It's for developers who need a separate operating system for agent tasks, controlled through an async Python API.

Helix is a paid, self-hosted platform for engineering teams coordinating coding agents. Agents work on separate tasks in parallel, while the team shares a view of their progress and reviews their work.