Prompts, redacted before they leave
Philter AI Proxy sits between your application and OpenAI, Anthropic, Gemini, Bedrock, Ollama, or an OpenAI-compatible API, and redacts each prompt before it leaves your network.
AI and LLM applications
Prompts, retrieved documents, and agent tool calls carry whatever personal data your users and records contain. Philterd redacts it on your side, before it reaches an LLM provider, a vector store, or a training set. That gives your security team a concrete answer when an AI feature comes up for review.
For applications that call LLMs
For AI agents and assistants
Philter AI Proxy sits between your application and OpenAI, Anthropic, Gemini, Bedrock, Ollama, or an OpenAI-compatible API, and redacts each prompt before it leaves your network.
The proxy can scan model responses too, and for each route you choose to redact what it finds, block the response, or pass it through with a warning in the log.
Run retrieved documents and training data through Philter before they reach a vector store or a fine-tuning set, so less personal data reaches a model that could repeat it.
An application calling LLMs
A drop-in proxy for LLM traffic. It is not an AI gateway, and it is designed to run alongside one, redacting on the last hop before traffic leaves your network.
About Philter AI Proxy →An agent or assistant
An MCP server that gives Claude Desktop, Claude Code, Cursor, and other MCP clients redaction tools to call from inside the agent’s tool loop.
About Philter MCP →RAG and data pipelines
Redacts documents through an API in your own cloud before they are indexed or used for training, launched from your cloud’s marketplace.
About Philter →A training corpus
We de-identify the corpus with you and measure the result against a gold standard built from your own records.
See the engagement →Free, ready-to-use policies from the open source policy library. Download and load into your Philter instance.
Redact personal data and special-category data as defined by the EU General Data Protection Regulation (GDPR) from documents and records.
Aggressive PII redaction for documents being fed into LLM training, fine-tuning, or RAG vector stores — preserves semantic structure with type tokens.
Redact PHI from user messages to a healthcare chatbot before they reach the LLM — preserves clinical meaning while removing identifiers.
Redact PII and PHI before any prompt reaches an LLM, keeping data on your own infrastructure. A self-hosted pipeline for chat, RAG, and AI agents.
Pointing a client at the proxy is one line. Where it sits relative to your AI gateway, and what it does with streaming responses, are the parts to get right.
Philter MCP exposes PII and PHI redaction as Model Context Protocol tools that Claude Desktop, Claude Code, Cursor, and other MCP clients call mid-conversation.