Automorphic

Automorphic provides a suite of solutions for language models, including Infuse knowledge into language models with just 10 samples, Self Improving models, Blazing Fast loading/stacking of fine-tuned adapters, OpenAI API Compatible, and Automorphic Hub for publicly shared models. It also provides Aegis, a firewall for models, which can detect prompt injections, prompt and PII leakage, toxic language, and more.