Inferwall

What Inferwall is

Inferwall is a self-hosted AI firewall for checking inputs and outputs in LLM applications. It scans for threats such as prompt injection, jailbreaks, data leakage, and unsafe content using heuristic, machine-learning, semantic, and configurable LLM-judge layers. It can run as a Python SDK, HTTP server, or transparent reverse proxy. Listed wrappers include OpenAI, Anthropic, LangChain, and FastAPI, with additional integrations such as Ollama, Hugging Face, LlamaIndex, Pydantic, vLLM, and Mistral. Teams can set allow, flag, or block thresholds for each route and add or override signatures and version policies under ~/.inferwall/. The Lite profile is about 8 MB and needs no GPU; Standard adds about 730 MB of models, while Full adds the LLM-judge layer and requires LLM credentials. The site reports that the Rust heuristic engine runs in under 0.3 ms at p99. The engine is Apache 2.0 licensed, and community signatures use CC BY-SA 4.0. Inferwall cautions that detection is imperfect and positions the product as one part of a defense-in-depth strategy.