Verdict
Decision
Choose Limina on-premises when its documented boundary matches the job.
Limina on-premises is a commercial local-deployment option for organizations that want vendor-supported de-identification. The cited sources describe it as a locally deployable redaction option. Choose it when vendor-supported local deployment is the job. Local availability and commercial terms require a vendor agreement.
Setup
Start by confirming deployment and the data path.
Confirm this setup detail before you build a routine: Container in customer on-premises environment or VPC. Then verify the processing boundary — Commercial entity detection and de-identification engine — and keep the first sample low-risk until the account, device, or runtime behavior matches the source description.
Workflow
Workflow: detect and de-identify sensitive data; this comparison covers text.
Use Limina on-premises to detect and de-identify sensitive data; this comparison covers text. Customization is described as enterprise model-version pinning and guided integration/tuning. Keep the workflow small enough to review its output and control settings; the cited sources do not establish a universal quality or speed result.
Alternatives
Compare Limina on-premises by the constraint that decides the work.
The five-guide table retains the current guide and four siblings in the locally deployable text redaction group. Values come from the cited source cells; an Unknown cell means the sources did not support a stronger statement.
| Guide | Workflow | Deployment | Input | Entry cost | Method | Customization | Limitation |
|---|---|---|---|---|---|---|---|
| OpenAI Privacy Filter | Model-based text redaction with a local CLI and Python API. | Local CPU or GPU; checkpoints downloaded if absent. | Text strings, files and pipes. | Open repository; compute and operational costs remain. | Token classification with span decoding. | Runtime precision/recall presets, evaluation and fine-tuning commands. | Validate detection on the target corpus; community scores change with matching criteria. |
| Presidio | PII identification followed by configurable anonymization. | Python module or self-hosted HTTP service/container. | Text and detected entity spans. | Open-source deployment; self-hosting/integration cost separate. | Analyzer plus separate anonymizer operators. | Replace, mask, redact or encrypt; reversible operators need corresponding metadata and keys. | Anonymizer acts on supplied detections; missing detections are not repaired by replacement. |
| scrubadub | Replace personally identifiable spans in free text. | Python package invoked inside local scripts. | Free-text strings. | Apache-2.0 software; dependency and operation costs separate. | Detectors identify spans; postprocessors control replacement. | Optional address, spaCy and Stanford detector packages; locale configuration. | Extra detector dependencies are needed for some entity types. |
| Limina on-premises | Detect and de-identify sensitive data; this comparison covers text. | Container in customer on-premises environment or VPC. | Text; product also supports documents, images and audio. | Enterprise custom pricing; free hosted Starter is not the local-deployment price. | Commercial entity detection and de-identification engine. | Enterprise model-version pinning and guided integration/tuning. | Local availability and commercial terms require vendor agreement. |
| Philter UCSF | Remove protected health information from clinical plain text. | Local Python command-line package. | Plain-text file or directory of clinical notes. | BSD-3-Clause software; integration and compute separate. | Configurable filtering pipeline with optional evaluation annotations. | Filter configuration and input/output paths. | Clinical-domain focus; general chat/email quality is not established. |
Review signal
Independent context for Limina on-premises is bounded.
The bounded cited sources contain no independent current-version review or community evaluation for Limina on-premises. Its fit is consequently a documented capability read, with no tested ranking attached.
- No independent current-version review or community evaluation was included for Limina on-premises among these cited sources.
- Treat official capability statements as the decision input and run your own representative check before a consequential rollout.
Caveats
Keep the source boundary visible while you decide.
The current cited cost statement is: Enterprise custom pricing; free hosted Starter is not the local-deployment price. Privacy or processing control is described as: Privacy controls are not fully described in the cited sources. The principal product boundary is: Local availability and commercial terms require vendor agreement. These are source-qualified statements, not an installation result, benchmark, security audit, or retention guarantee.
- No independent current-version benchmark or installed container verification.
- Underlying detector implementation and exact local hardware requirements not captured.
First check
Make the first adoption check specific to Limina on-premises.
Run a labeled sample from the target corpus through detection and replacement, then inspect misses, over-redaction, and logs before sending real data through the pipeline.
Receipts
Claim table
| Where | Claim | Confidence | Source | Caveat |
|---|---|---|---|---|
| Workflow | Detect and de-identify sensitive data; this comparison covers text. | High | Limina | Source-qualified product description; no independent performance test was run. |
| Setup | Container in customer on-premises environment or VPC. | High | Limina | Source-qualified product description; no independent performance test was run. |
| Setup | Text; product also supports documents, images and audio. | High | Limina | Source-qualified product description; no independent performance test was run. |
| Decision | Enterprise custom pricing; free hosted Starter is not the local-deployment price. | High | Limina | Observed source wording; regional pricing, billing cadence, and future plan changes are not inferred. |
| Workflow | Commercial entity detection and de-identification engine. | High | Limina | Source-qualified product description; no independent performance test was run. |
| Workflow | Enterprise model-version pinning and guided integration/tuning. | High | Limina | Source-qualified product description; no independent performance test was run. |
| Caveats | Local availability and commercial terms require vendor agreement. | High | Limina | Do not infer that the free API tier includes the container. |
Sources
How this was built
| Publisher | Source | Type | Accessed |
|---|---|---|---|
| OpenAI | Privacy Filter repository and CLI | Official | 2026-10-18 |
| Data Privacy Stack | Presidio overview | Official | 2026-10-18 |
| Data Privacy Stack | Presidio Anonymizer | Official | 2026-10-18 |
| LeapBeyond | scrubadub README and license | Official | 2026-10-18 |
| scrubadub maintainers | scrubadub stable documentation | Official | 2026-10-18 |
| Limina | Pricing and deployment FAQ | Official | 2026-10-18 |
| UCSF / BCHSI | Philter UCSF README | Official | 2026-10-18 |
| Gaurav Vij / GitHub | GLiNER large-v2.1 vs Privacy Filter case study | Community | 2026-10-18 |
| UCSF authors / JAMIA Open | A certified de-identification system for all clinical text documents | Review | 2026-10-18 |