Tag
Plano is an open-source proxy that sits between AI agents and LLM providers to cut costs through intelligent routing, guardrail filtering, and cost-aware selection, all configured via a single YAML file without modifying agent code.
DT-Guard introduces a reasoning-active training, reasoning-free inference paradigm for LLM safety guardrails, achieving strong F1 scores on safety benchmarks with a 4B backbone model, outperforming larger baselines.
SingGuard is a multimodal guardrail system from Ant Group that treats safety policy as an input, allowing dynamic adaptation via natural language. It is released under Apache 2.0 and covers text and image modalities.
SingGuard is a policy-adaptive multimodal LLM guardrail model for text, image, and multilingual safety moderation, featuring dynamic reasoning and a new benchmark SingGuard-Bench. It achieves state-of-the-art results across multiple datasets.
This paper introduces CHILLGuard, a fine-grained Chinese LLM content safety guardrail built on a new 5-macro, 31-micro category risk taxonomy and a scalable multi-stage data construction pipeline. The model achieves state-of-the-art performance, improving F1 score by 15.92% over existing baselines.