AI Defense Stack

GenAI data-leak prevention & privacy

Limina (Private AI): container PII detection and redaction engine

Limina is a container PII detection and redaction engine from Limina. It is a commercial product offered as: Self-hosted, On-prem, API. Pricing model: freemium. The vendor's page now calls it Limina.

  • Last reviewed
Visit Limina (opens in a new tab) Documentation (opens in a new tab)
Commercial Freemium Now Limina Layer 5: Data protection

Best for

Teams that need PII, PHI and PCI de-identification of text, files and audio that runs inside their own VPC or on-premises

Ownership

The private-ai.com site redirects to getlimina.ai, and the documentation at docs.private-ai.com is branded Limina. Neither page states a rename date or reason. Source, checked October 21, 2026: docs.private-ai.com (opens in a new tab)

Consider instead if

  • You want a free open-source library for PII detection that you can modify yourself. See Presidio.

What Limina does

Limina, whose site was previously at private-ai.com, sells a container-based engine that detects and redacts sensitive data. The documentation describes a stateless container with a REST API that finds personal, health and payment data in unstructured and structured data, in text, PDFs, images and audio. The container runs in the customer's own VPC or on-premises, with Kubernetes guides in the docs. Processed text can be replaced with markers, masked, or swapped for synthetic values. Pricing starts with a free Starter plan limited to 75 API calls per day, and Batch and Enterprise plans are priced by volume. It is closed source.

This summary is our own wording of the sourced facts on this page.

Key facts

Each value links to the page that states it, with the date we checked it.

Vendor
Limina Source, checked October 21, 2026: getlimina.ai (opens in a new tab)
Status
Renamed Source, checked October 21, 2026: docs.private-ai.com (opens in a new tab)
Current name
Limina Source, checked October 21, 2026: docs.private-ai.com (opens in a new tab)
Ownership
The private-ai.com site redirects to getlimina.ai, and the documentation at docs.private-ai.com is branded Limina. Neither page states a rename date or reason. Source, checked October 21, 2026: docs.private-ai.com (opens in a new tab)
Open source
No: closed source (proprietary) Source, checked October 21, 2026: docs.getlimina.ai (opens in a new tab)
Latest release
Not documented in the sources we checked
Deployment
Self-hosted, On-prem, API Source, checked October 21, 2026: getlimina.ai (opens in a new tab)
Pricing model
Freemium: Starter plan is free, up to 75 API calls per day (10 per minute). Batch is volume priced by quote. Enterprise has custom, committed volume pricing. Billed monthly in USD, based on data volume and deployment model. (as listed on October 21, 2026; check the vendor for current pricing) Source, checked October 21, 2026: getlimina.ai (opens in a new tab)
Website
getlimina.ai Source, checked October 21, 2026: getlimina.ai (opens in a new tab)
Documentation
docs.getlimina.ai Source, checked October 21, 2026: docs.getlimina.ai (opens in a new tab)
API reference
docs.getlimina.ai Source, checked October 21, 2026: docs.getlimina.ai (opens in a new tab)
Quickstart
docs.getlimina.ai Source, checked October 21, 2026: docs.getlimina.ai (opens in a new tab)
Security page
docs.getlimina.ai Source, checked October 21, 2026: docs.getlimina.ai (opens in a new tab)
Attestations or disclosure
Company is ISO 27001:2022 and SOC 2 Type 2 certified for its internal operations and processes Source, checked October 21, 2026: docs.getlimina.ai (opens in a new tab)

Capabilities

As documented by the vendor or project. The tag is our label from a controlled vocabulary.

Integrations

Where Limina fits in our AI security layers

Our analysis

Our editorial model, not a standard. The primary layer follows the category, except for tools whose main documented job is detection and response; other layers rest on a capability the sources document. How the model works.

AI security layers that Limina covers, with the role, how each applies and what it rests on
LayerRoleHow it appliesBased on
L5 Data Data protection Primary Keep sensitive data out of prompts, uploads, retrieval and training data, or remove and tokenize it first. Follows its category, GenAI data-leak prevention & privacy

OWASP LLM Top 10 mapping

Our analysis

The risk list is OWASP's (Top 10 for LLM Applications, 2025). The mapping is our analysis, and each row rests on a capability the sources document.

OWASP LLM risks mapped to Limina, with the capabilities each mapping rests on
RiskHow it appliesBased on
LLM02 Sensitive Information Disclosure Detects and redacts personal, health and payment data in text before it is passed on. Detects PII, PHI and PCI across 50+ entity types in 52 languages; Redacts detected entities by replacing them with markers or masking them with a character

Not mapped in our analysis: LLM07, LLM08. These are risks we expect tools in this category to cover; the sources we checked do not document a matching capability.

Alternatives and related tools

More in GenAI data-leak prevention & privacy, ranked within the category by Coverage Score.

Protecto

Protecto

Commercial
  • SaaS
  • On-prem
  • API

Detects sensitive data and tokenizes or masks it before it reaches LLMs, RAG pipelines and agents.

Best for: Teams that want an API that tokenizes or masks sensitive data before it reaches LLMs and RAG pipelines and restores it afterwards

Coverage Score 70 out of 100
  • LLM02 Sensitive Information Disclosure
  • LLM08 Vector and Embedding Weaknesses

Reviewed

Presidio

Data Privacy Stack

Open sourceMIT
  • Library
  • Self-hosted

Finds and masks personal data in text, images and structured data, and you run it yourself.

Best for: Engineering teams that want a free, self-hosted library to detect and anonymize PII before text reaches a model or a log

Coverage Score 67 out of 100
  • LLM02 Sensitive Information Disclosure

Reviewed

Tonic Textual

Tonic.ai

Commercial
  • SaaS
  • On-prem
  • API
  • Library

Detects sensitive entities in text and audio, then redacts or replaces them before data reaches an LLM.

Best for: Teams preparing free text, documents or call audio for LLM training, RAG or testing that need entity-level redaction or synthetic replacement

Coverage Score 60 out of 100
  • LLM02 Sensitive Information Disclosure

Reviewed

Limina FAQ

Is Private AI the same as Limina?

The private-ai.com site redirects to getlimina.ai and its documentation host is branded Limina, so we list them as one product. Neither page states a rename date or reason.

Is there a free plan?

Yes. The pricing page lists a free Starter plan with up to 75 API calls per day. Batch and Enterprise plans are priced by volume.

Where does it run?

The documentation describes a container that runs in the customer environment, and the homepage says it runs in your VPC or on-prem.

Key facts you can cite

We have no commercial relationship with Limina.

Sources & last reviewed

Last reviewed . We compile from the vendors' own public pages and repositories and we do not run the products. Source links open in a new tab. Found a mistake? Report a correction.