01
Manual review is slow
Long documents make anonymization repetitive, expensive and inconsistent.
Local-first document privacy
Detect sensitive data.
Share only what's needed.
RedactGuard uses a local LLM to detect standard or custom PII, lets you review every finding, and creates a minimized document before sharing.
Local processingCustom PIIHuman review
Detect locally → review → redactNothing leaves automatically
The problem
Sensitive data is not a fixed list.
What must be protected changes by document, industry, organization and workflow. That makes detection both a privacy problem and a maintenance problem.
02
Static rules are hard to adapt
New PII often means new regex, mappings, exceptions and application logic.
03
Cloud AI changes the privacy boundary
The original sensitive document must leave the machine before it can be analyzed.
The hidden cost: every change in what counts as sensitive can become a software change.
The solution
Define what is sensitive.
RedactGuard finds it locally.
Standard identifiers or domain-specific information can be expressed through profiles and custom PII instructions used by the local LLM.
For many taxonomy changes, you update the definition instead of building another hard-coded detector.
1
Define PIIUse a profile or add custom sensitive categories.2
Detect locallyThe GGUF model analyzes the document on the machine.3
ReviewThe model suggests. The user confirms.4
ExportOnly the minimized result moves to the next workflow.Why it matters
Privacy, adaptability and control.
01
Private by design
The document can be processed with local inference, without making cloud AI the default path for sensitive content.
02
Adaptable by configuration
New or changing PII can often be handled by updating the profile or prompt, instead of adding another detector.
Change the definition, not the software.03
Human-controlled
AI accelerates detection, but the user decides what is actually removed before export.
Product proof
Load. Review. Export.
The workflow stays visible and reversible until the user confirms the final redactions.
1 · LOAD
Choose the document and profile
Start from a built-in domain profile or a custom detection definition.
2 · REVIEW
Inspect every finding
Keep, remove or adjust what the local model identified as sensitive.
3 · EXPORT
Share the minimized result
Export only after the redaction choices have been explicitly reviewed.
Under the hood
Local by architecture.
Once the product idea is clear, the implementation is intentionally simple: UI, document processing, and local inference have separate responsibilities.
React / Vite
Upload, profile selection, human review and export workflow.
FastAPI + Docling
Document conversion, sessions, PII orchestration, redaction and caching.
Local GGUF LLM
Contextual PII detection through llama-cpp-python, including profile and custom-type instructions.
RedactGuard is an experimental privacy tool, not a compliance guarantee. Local AI can miss, misclassify or over-detect sensitive information, so results still require human review.
Local-first data minimization
Define what is sensitive. Share less.
RedactGuard turns local AI into a configurable privacy workflow: define → detect → review → redact → export.