Apps similar to WildGuard include Statewright, which is open source with a free version. Other options are Llama Guard, Toxic Prompt RoBERTa, ShieldGemma and MoorAI. In total there are five Large Language Model (LLM) Tools like WildGuard for self-hosting, Mac, Windows and the web.
State machine guardrails that control which tools your AI agent can use in each phase. Define a workflow once, enforce it across Claude Code, Codex, Cursor, opencode, and Pi.
Llama Guard is an LLM-based input-output safeguard model geared towards Human-AI conversation use cases.
A text classification model that can be used as a guardrail to protect against toxic prompts and responses in conversational AI systems.
ShieldGemma is a set of instruction tuned models for evaluating the safety of text and images against a set of defined safety policies. You can use this model as part of a larger implementation of a generative AI application to help evaluate and prevent generative AI...
On-device, content-free security for AI coding agents — it reviews prompts, files and MCP tool-calls locally, before anything leaves the machine.
United States
