Protecto + LibreChat

Mask sensitive data in LibreChat before it reaches the model

Protecto Privacy Gateway for AI Chat runs between LibreChat and whichever model you connected. Sensitive values are masked before the model sees them and unmasked on the way back.

The Gateway is not a LibreChat feature. It sits behind the chat interface, so the interface stays yours to change.

LibreChatReal data on screen
Protecto Privacy GatewayMasks, then unmasks
Your modelMasked values only
On your screen in LibreChat

Summarize the claim for Maria Lopez, account 4821-7730, callback 415-555-0142.

Real valuesMasked valuesIllustrative example
Trusted by regulated enterprises & agentic platforms
Inovalon
Automation Anywhere
Citrix
Bank Of Muscat Logo
Dell

Does LibreChat mask sensitive data by default? No.

LibreChat is open-source and self-hosted, which keeps your data on your own infrastructure. It does not detect, mask, or redact sensitive data before sending it to a connected model.

Protecto closes that gap: it masks PII, PHI, and other sensitive data in every prompt and uploaded document using entity-level detection and reversible tokenization, before LibreChat sends anything to OpenAI, Anthropic, Google, Azure, or Bedrock.

The response comes back masked, and Protecto unmasks it before the user sees it. The user works with real data. The model only ever sees masked values.

Protecto + LibreChat product tour
Protecto + LibreChat product tour

Why teams run LibreChat

Infrastructure control, on your own terms

LibreChat is open source and self-hosted. Teams choose it to get every model provider behind one interface, on their own infrastructure.

Every model provider, one interface.

OpenAI, Anthropic, Google, Azure, Bedrock, and more.

Your infrastructure, your costs.

No per-seat SaaS pricing or vendor lock-in.

Enterprise auth in the free core.

SSO, SAML, LDAP, and OAuth ship with it.

What’s the gap between self-hosting and data protection?

LibreChat gives you infrastructure control, not content protection. Every prompt, document, and response can still carry sensitive data straight to the model.

Self-hosting LibreChat solves where the data lives. It does not solve what the connected LLM sees.

How the Gateway works with LibreChat

The Gateway is deployed in the request path between LibreChat and your model providers. Inside LibreChat it surfaces as a selectable secure chat mode.

LibreChat workflow with Protecto. The user chats in LibreChat, inside your infrastructure. LibreChat connects to files and RAG and to tool calls, and Protecto masks files, embeddings, RAG content, tool arguments and tool results. Prompts and instructions are masked in Protecto Privacy Gateway, and only masked values leave for LLM calls to any provider. Streamed responses come back protected, and the Gateway automatically rebuilds masked conversation history.Your infrastructureLLM callsAny providerMasked values onlyOpenAIClaudeGeminiGrokDeepSeekKimiOllama& moreUserFiles & RAGUploads, retrieval,embeddingsTool callsMCP, internal APIsLibreChatChat, orchestration, historyProtecto PrivacyGatewayMASK · UNMASKPrompt + instructionmaskingAutomatically rebuildmasked conversationhistoryOnly maskedvalues leaveStreaming responseprotectionMask files, embeddings, & RAG contentTool args + results re-maskedMaria Lopez[PERSON_7a1][PERSON_7a1]Maria LopezLibreChat workflow with Protecto. The user chats in LibreChat, inside your infrastructure. LibreChat connects to files and RAG and to tool calls, and Protecto masks files, embeddings, RAG content, tool arguments and tool results. Prompts and instructions are masked in Protecto Privacy Gateway, and only masked values leave for LLM calls to any provider. Streamed responses come back protected, and the Gateway automatically rebuilds masked conversation history.Your infrastructureUserLibreChatChat, orchestration, historyFiles & RAGUploads, retrievalTool callsMCP, internal APIsMasked before it leavesProtecto Privacy GatewayMASK · UNMASKPrompt + instruction masking.Masked history rebuilt automatically.Only masked values leaveLLM callsAny provider, masked values onlyOpenAIClaudeGeminiGrokDeepSeekKimiOllama& more
LibreChat workflowProtecto interceptionMasked before it leaves

Every prompt in that mode routes through the Gateway before it reaches the model. Unmasking uses controlled boundary resolution authorized by a per-user Protecto token, so your team works with real data and the model never holds it.

01

You type

You type a prompt containing sensitive data, same as always.

02

Protecto masks

Protecto detects and masks the sensitive entities before the prompt leaves LibreChat.

03

The model sees masked values

The model, whether that’s OpenAI, Anthropic, Google, or another connected provider, only ever sees masked values.

04

The response returns

The model’s response comes back with masked data intact.

05

You read real data

Protecto unmasks the response before you see it. You read your original data. The model never did.

You can inspect every step

Protecto shows the masked prompt, the specific values it identified and masked, and the unmasked response, side by side with the original.

In a document: Upload a file and ask the model to summarize it. Protecto masks the sensitive content in the document before it’s sent for summarization. You see the summary with real names, numbers, and details. The model generated it from masked values only.

Behind the Scene
Values Protecto identified and masked

Why this matters

For engineering and platform teams

You don’t rebuild PII detection and masking logic for every model you connect to LibreChat. Protecto sits in the request path once and covers every model behind it, including new ones you add later. The Gateway is decoupled from the chat interface itself, so swapping LibreChat for another interface later doesn’t mean rebuilding your protection layer. It’s infrastructure you point at, not a plugin you’re locked into.

For security and compliance teams

Self-hosting LibreChat gives you infrastructure auditability. Protecto adds content-level protection on top of it, so sensitive data never reaches any model, internal or external, in the clear. You get visibility into exactly what was masked, when, and in which conversation, which is the evidence a HIPAA or GDPR review actually asks for.

For end users

The LibreChat chat experience doesn’t change. You work with real data in the interface you already use. Protecto’s masking and unmasking happens behind the scenes, in real time.

Model support

Protecto Privacy Gateway for AI Chat works with any model connected to LibreChat, including OpenAI, Anthropic, Google, Azure, and AWS Bedrock. As you add models or providers to your LibreChat instance, they inherit the same protection automatically.

LibrechatOpenAI
LibrechatClaude
LibrechatGemini
LibrechatDeepSeek
LibrechatGrok
& more
Security & compliance

Built for regulated data at enterprise scale.

Protecto combines data protection, audit logs, and ready-to-use policies for regulated data, whether deployed as SaaS, on-prem, in a private cloud, or air-gapped.

SOC 2 Type II

Audited controls

ISO 27001

Certified ISMS

HIPAA

BAA available

GDPR

EU data ready

DPDP

India privacy law

CCPA / CPRA

US privacy
Independently verified to outperform AWS Comprehend and Microsoft Presidio · audit logs on every scan, mask, and unmask.

Common questions

Is this a LibreChat plugin?

No. Protecto Privacy Gateway for AI Chat is decoupled from the chat interface. LibreChat is the integration available today; the Gateway runs the same way behind any interface that supports it.

No. LibreChat has no built-in data masking. Protecto adds a masking layer inside LibreChat’s secure chat mode.

Yes, for what reaches the model. Retrieved content is masked before it enters the prompt, and text is masked before embedding. The original file stays in LibreChat’s own storage, outside the Gateway.

No. Masking happens on content moving through the chat path, not on files already sitting in storage. Don’t rely on the Gateway to retroactively clean sensitive files you’ve already uploaded elsewhere.

Combine LibreChat’s native SSO, SAML, and LDAP with Protecto for content-level protection. Infrastructure control alone doesn’t stop sensitive data from reaching the model.

Yes. OpenAI, Anthropic, Google, Azure, and AWS Bedrock, since masking happens before the request leaves LibreChat, independent of provider.

No. Uploaded documents are masked before summarization, and the response is unmasked before the user sees it.

Add Protecto to your LibreChat

Talk to us about adding Protecto to your LibreChat deployment.

New: run any AI model without exposing real values.
See how it works