Data as of Sep 29, 2026 · Based on 3,031 AI responses · See how Parse measures this
Philter AI Proxy is an open-source on-premises proxy that acts as an airlock for LLM traffic, redacting PII from prompts before they leave your network and scanning responses on the way back. It supports major providers (OpenAI, Anthropic, and Amazon Bedrock) and runs as a Docker container or via Docker Compose with a configurable setup. It is part of Philterd's suite of privacy and redaction tools, providing guardrails, policy enforcement, and PII protection across AI workflows.
<1%No change
of AI answers about Philter AI Proxy and its rivals. Week of Sep 21
The market map · 5 of 100 labelled
LLM Security and Governance PlatformsMentioned in · week of Sep 21
“Philter AI Proxy: A self-hosted, open-source proxy designed to run on your local infrastructure”
“Philter AI Proxy acts as a proxy for multiple LLM providers, redacting PII before forwarding requests while supporting streaming and audit logs.”
“Philter AI Proxy: An open-source, self-hosted proxy tailored explicitly to strip PII from outbound LLM prompts”
We need to redact PII from user inputs before sending them to a third-party LLM. What's the best PII redaction API with high accuracy?
PresidioAmazon ComprehendGoogle Cloud Sensitive Data Protection
I am planning to optimize our token usage costs. Who offers LLM caching and semantic caching tools?
GPTCache
AI mentioned Philter AI Proxy in <1% of answers about Philter AI Proxy and its rivals in the week of Sep 21.
Philter AI Proxy is a product of Philterd.
Where Philter AI Proxy ranks in AI
Excerpts where Philter AI Proxy appeared in the AI's answer
Philter AI Proxy: A self-hosted, open-source proxy designed to run on your local infrastructure
Philter AI Proxy acts as a proxy for multiple LLM providers, redacting PII before forwarding requests while supporting streaming and audit logs.
Excerpts where Philter AI Proxy appeared in the AI's answer
Philter AI Proxy: An open-source, self-hosted proxy tailored explicitly to strip PII from outbound LLM prompts