Petri is an alignment auditing agent for rapid, realistic hypothesis testing. It autonomously crafts environments, runs multi turn audits against a target model using human like messages and simulated tools, and then scores transcripts to surface concerning behavior.
United States
Llama Guard is an LLM-based input-output safeguard model geared towards Human-AI conversation use cases.
Wardstone is an LLM firewall and AI guardrail API that protects AI applications from prompt attacks, harmful content, data leakage, and suspicious links in a single inference call with ~30ms latency.
United Kingdom
WildGuard is an open, lightweight moderation tool for LLM safety that achieves three goals:
Privacy-focused browser extension monitoring conversations on top AI chat platforms, providing plain-English summaries and safety alerts instead of full transcripts.
United Kingdom
Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.
New Zealand
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...
A text classification model that can be used as a guardrail to protect against toxic prompts and responses in conversational AI systems.
Germany
EU
