Open-source Prompt Firewall — deflect up to 95% of redundant LLM traffic before it leaves your infrastructure. Documents: https://isartor-ai.github.io/Isartor/index.html

🔥 QFIRE — a prompt firewall for LLM applications (proxy + CLI + benchmark harness) in Rust (100+ firewall rules).

An open source inline security layer that sits between user applications and large language models (LLMs) to monitor, filter, and modify inbound prompts and outbound responses in real time.

An index and topic collection covering AI gateways — LLM routers, cost/usage controls, prompt firewalls, model fallback, and policy engines that sit between applications and AI model providers.