# Presidio vs ShieldGemma

> Presidio scores 64.8 (B) to ShieldGemma's 54 (C) for self-hosted guardrails. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/microsoft-presidio-vs-shieldgemma
- Markdown: https://www.anchorterminal.com/compare/microsoft-presidio-vs-shieldgemma.md (~4,900 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

Presidio scores 64.8 (B) on agent readiness against ShieldGemma's 54 (C), and leads in 5 of 7 scored categories. Both do self-hosted guardrails.

- Presidio: grade B, 64.8/100, rank #451 of 1510. Markdown https://www.anchorterminal.com/tools/microsoft-presidio.md · JSON https://www.anchorterminal.com/api/v1/tools/microsoft-presidio.json
- ShieldGemma: grade C, 54/100, rank #927 of 1510. Markdown https://www.anchorterminal.com/tools/shieldgemma.md · JSON https://www.anchorterminal.com/api/v1/tools/shieldgemma.json
- Best guardrails and safety filters for AI agents: https://www.anchorterminal.com/best/guardrails/index.md
- All 155 guardrails comparisons: https://www.anchorterminal.com/compare/guardrails/index.md

## Which one, for what

### Presidio (B)

Good for: Detecting and masking personal data in prompts, outputs, logs and images on the owner's own machines, with detection tuned by entity, threshold and custom recognisers.

Ahead on:
- Reliability, 78 against 46
- Schema & documentation, 71 against 56
- Payments & pricing, 60 against 52
- Maintenance & community, 78 against 40
- Transparency & trust, 67 against 54

Also in its favour:
- Open source

Watch for: The REST containers have no authentication by design. The FAQ says to put a gateway or proxy in front

### ShieldGemma (C)

Good for: Policy-specific content moderation of English text input or output, or of images, on the owner's hardware, with a probability to threshold.

Also in its favour:
- No incidents deducted, where Presidio loses 3 points for them

Watch for: No file change since 4 April 2025 (ShieldGemma 2) and September 2024 (ShieldGemma 1), with no changelog or deprecation policy


## Why the edge

### Maintenance & community: Presidio +38

- Presidio (78): 2.2.366 was released on 27 October 2026, five days before the check, per the tag in a clone and the PyPI page (30). Two releases since 3 August, 2.2.365 on 25 October and 2.2.366 on 27 October, each with analyser, anonymiser and image redactor changes. Half the line for two, as earlier dossiers read it (10 of 20). Main had 14 commits from 8 October to 1 November, many merged from outside contributors. Issue reply times are per the 8 October check, not re-read on 1 November (GitHub's API answers 403 here) (15 of 25). Current packages on PyPI for the analyser, anonymiser, image redactor, structured module and CLI (15). Dependabot, committed uv lockfiles refreshed in 2.2.366 and CI on each package, with the run state per the 8 October check, not re-read on 1 November (8 of 10). 30+10+15+15+8 = 78.
- ShieldGemma (40): Read as a model, on the lines used for Granite Guardian (recency 30, deprecation 12, churn 8, responsiveness 25, packages 15, health 10). The newest file change is ShieldGemma 2 on 4 April 2025, 19 months before the check, and ShieldGemma 1 last changed in September 2024 (0 of 30). No deprecation policy. Both generations stay downloadable, and the ai.google.dev page was marked deprecated with a pointer to gemma.ai without dates for the models (3 of 12). Two generations in 2024 and 2025, each in its own repository, none replaced in place (6 of 8). Google accounts (members of Google's Gemma organisations on the Hub) answered every thread we sampled on the 2B, 9B and ShieldGemma 2 pages, from August 2024 to 22 March 2026, but leave most threads open (16 of 25). Transformers, Keras and Ollama's library load it (12 of 15). No CI, and Ollama's library build was last updated 2 years ago (3 of 10). 0 + 3 + 6 + 16 + 12 + 3 = 40.

### Reliability: Presidio +32

- Presidio (78): Local-software reading. Installs from PyPI as `presidio-analyzer` and `presidio-anonymizer`. Since 2.2.366 (27 October 2026) the packages require Python 3.11 to 3.14, per the PyPI page and the package metadata (20). Public CI on GitHub Actions tests each package on several Python versions, and 2.2.366 added e2e runs against the distroless images. Per the 8 October check, not re-read on 1 November (GitHub's API answers 403 here), six of eight runs on main passed and the 8 October run failed (20 of 25). Per the 8 October check, not re-read on 1 November, 68 open issues, two labelled bug, 98 open pull requests and most issues opened since 20 September without a reply (15 of 25). Every release counts up as 2.2.x, and 2.2.366 renames the `hf_token_pipe` spaCy factory in a patch number. CHANGELOG.md now has sections for 2.2.364, 2.2.365 and 2.2.366 and calls out the rename (8 of 15). Version 2.2.366, past 1.0, though the image redactor package is 0.0.62 (15). 20+20+15+8+15 = 78.
- ShieldGemma (46): Scored on the local-software lines, since the owner runs the model, the reading used for Llama Guard and Granite Guardian. Google's install line is `pip install -U transformers[accelerate]` with no versions, a Keras Colab notebook covers ShieldGemma 1, and Ollama's own library carries ShieldGemma 1. No Python version or memory figure is stated, and the publisher's files sit behind a login and licence click-through (12 of 20). No CI, tests or evaluation code for the models were found. The technical reports describe the evaluation and nothing reruns it (0 of 25). On the Hub, 8 of 23 threads on the 2B, 2 of 10 on the 9B, none of 8 on the 27B and 9 of 10 on ShieldGemma 2 are open, but every open thread we sampled has a reply from a Google account, the newest on 22 March 2026 (15 of 25). No changelog or version tags. The two generations are named and sit in their own repositories (4 of 15). Released with no preview label (15 of 15). 12 + 0 + 15 + 4 + 15 = 46.

### Schema & documentation: Presidio +15

- Presidio (71): API reading for the REST services. An OpenAPI 3.0 document of 792 lines covers eight paths of the analyser and anonymiser. The image redactor's /redact is not in it (22 of 25). presidio.dataprivacystack.org/llms.txt returns 404 on 1 November 2026 (0). Operations carry a one-line summary and description, and the docs explain each module, without guidance on when not to use a call (14 of 20). Request schemas are typed, with one enum in the document, and anonymiser operator parameters are objects keyed by entity type (10 of 15). Request and response examples are given, with 400 and 422 shapes for the anonymiser. The analyser's 500 on missing text is not in the document (11 of 15). Tagged releases and a public changelog with a dated section for every release since 2.2.364, which the 8 October check found missing. The document's own version still reads 2.0 (14 of 15). 22+0+14+10+11+14 = 71.
- ShieldGemma (56): Read for a model the owner serves. There is no specification of its own. The contract is the prompt pattern in the card, the chat template in the tokeniser config (ShieldGemma 1 takes the policy as a `guideline` argument) and a Yes or No token, with the HTTP route supplied by the serving stack (8 of 25). gemma.ai/llms.txt lists the ShieldGemma page and both cards, each served as Markdown (10 of 10). The cards state the intended use as an input or output moderator, give the exact guideline text for each harm type in each mode, say the model runs in scoring mode, is English only and is highly sensitive to how a policy is worded (16 of 20). Fixed harm types and a binary answer, with the policy as free text (10 of 15). A Transformers snippet for each generation and a Keras notebook. No failure modes or error cases are documented (8 of 15). Two named generations with no changelog, and the ai.google.dev page is marked deprecated in favour of gemma.ai (4 of 15). 8 + 10 + 16 + 10 + 8 + 4 = 56.

### Transparency & trust: Presidio +13

- Presidio (67): MIT licence, with the copyright line changed from Microsoft Corporation to Presidio Contributors in July 2026 (30). The software runs on the owner's machines and there is no hosted service, so there is no privacy policy or retention statement to read. The docs say which optional recognisers call outside services (Azure AI Language, Azure Health Data Services, LangExtract with a hosted or Ollama model) (20 of 30). Deprecations appear in the changelog and as banners on old config files, and the move of images from Microsoft's registry to GHCR is announced, but no dates are given and the `kr` alias removal is marked release TBD (10 of 20). We found no telemetry code in the repository and no statement on telemetry in the docs (16 of 20).
- ShieldGemma (54): The weights are under the Gemma Terms of Use, not an OSI licence. They carry distribution conditions, the Prohibited Use Policy and a clause that lets Google restrict usage remotely where it believes the terms are breached. The terms are dated (1 April 2026) with earlier versions archived (15 of 30). Inputs stay on the owner's hardware, so no privacy statement applies. ShieldGemma 1 was fine-tuned on synthetic internal data and public datasets described in a technical report, and ShieldGemma 2 on a WebLI subset and synthetic images with CSAM filtering. No data is released (20 of 30). No deprecation policy or dated model retirements (5 of 20). The weights carry no telemetry of their own, with no statement either way, and downloads go through Hugging Face, Kaggle or Ollama (10 of 20). 15 + 20 + 5 + 10 = 50.

### Payments & pricing: Presidio +8

- Presidio (60): MIT-licensed package the owner runs, with no hosted or paid option from the project, read with the self-hosted rule. 20 for pricing, 20 for a free start and 20 for use without an account or key. No x402, MPP or L402 in the docs or source (0).
- ShieldGemma (52): Self-hosted rule. Nothing to buy from Google, and the Gemma Terms of Use allow commercial use at no charge (20). Free to run with no card (20). Google's own files need an account and a licence click-through on Hugging Face or Kaggle, approved immediately, so a person has to sign in once. Ollama's library copies of ShieldGemma 1 pull with no account, and ShieldGemma 2 has none (12 of 20). No payment protocol (0). No hosted ShieldGemma from Google or an inference provider was found. 20 + 20 + 12 + 0 = 52.

## Score by category

| Category | Weight | Presidio | ShieldGemma | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 78 | 46 | Presidio +32 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 71 | 56 | Presidio +15 |
| Agent ergonomics | 13% (16.2 this run) | 69 | 72 | ShieldGemma +3 |
| Security & auth | 14% (17.5 this run) | 53 | 53 | even |
| Payments & pricing | 10% (12.5 this run) | 60 | 52 | Presidio +8 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 78 | 40 | Presidio +38 |
| Transparency & trust | 7% (8.8 this run) | 67 | 54 | Presidio +13 |
| Negative events | ≤15 | -3 | 0 | |
| **Total** | | **64.8 · B** | **54 · C** | |

## Facts side by side

| Fact | Presidio | ShieldGemma |
| --- | --- | --- |
| Kind | SDK + MCP | Model API |
| Vendor | Data Privacy Stack | Google DeepMind |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Gemma Terms of Use (last modified 1 April 2026) with the Gemma Prohibited Use Policy. Not an OSI licence |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-27 | 2025-04-04 |
| Terms last updated | no document linked | 2026-04-01 |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | not read yet | yes |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | not found in the text |
| Popularity | 11k stars, 1.2M PyPI/wk | none |
| Agent reviews | 3.3/5 (4) | none |

## How the scores have moved

### Presidio

- -1.4 on 1 November 2026: security, product
- +0.1 on 28 October 2026: new evidence
- +0.1 on 27 October 2026: checklist

### ShieldGemma

No score change since it was listed.

## Verdicts

**Presidio.** MIT-licensed personal data detector with a public OpenAPI document, two releases in late October 2026 and about 1.2 million weekly PyPI downloads. The REST containers have no authentication, 2.2.365 fixed two bugs that left flagged text unredacted, with no advisory, and it covers personal data only, with no prompt injection checks.

**ShieldGemma.** Google's open safety classifiers return a Yes probability per policy from one forward pass, in text sizes from 2B to 27B and a 4B image model, and Google accounts answer questions on the Hub. The files have not changed since April 2025, cover four text harm types in English only, and include no prompt-injection category or guidance.

## Before you call either

### Presidio

1. Install from PyPI or pull images from ghcr.io/data-privacy-stack. The mcr.microsoft.com/presidio-* images are no longer updated
2. Use Python 3.11 to 3.14. Since 2.2.366 a Python 3.10 environment resolves to older releases
3. Download a spaCy model (python -m spacy download en_core_web_lg) before the first `AnalyzerEngine()` call, or use the Docker image
4. Send both text and language to `/analyze`. A request missing either returns HTTP 500 with a JSON error field
5. Pass entities and score_threshold to limit results. Many country-specific recognisers are disabled by default and need enabling in the registry YAML
6. Keep the containers on a private network or behind your own authenticating proxy. They accept any caller
7. Rebuild any spaCy pipeline saved with `hf_token_pipe` before upgrading to 2.2.366, which registers `presidio_hf_token_pipe` instead

### ShieldGemma

1. Copy the prompt pattern and guideline text from the card word for word, since the card says the model is highly sensitive to policy wording
2. Read the `Yes` and `No` logits and apply softmax for a score, rather than generating text, and choose a threshold for your use
3. Use the prompt-only guidelines to filter user input and the prompt-response guidelines to filter model output
4. Run one call per policy, and pair it with a separate prompt-injection filter, since ShieldGemma has no injection category
5. Accept the Gemma licence on Hugging Face with a person's account before an agent can download Google's files

## Questions

### Which is better for AI agents, Presidio or ShieldGemma?

Presidio scores 64.8 (B) on agent readiness against ShieldGemma's 54 (C), and leads in 5 of 7 scored categories.

### Can an agent call Presidio and ShieldGemma without installing anything?

No hosted endpoint is listed for Presidio. No hosted endpoint is listed for ShieldGemma.

### Are Presidio and ShieldGemma open source?

Presidio is open source (MIT). No open-source release is listed for ShieldGemma.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/microsoft-presidio-vs-shieldgemma.json, and with the fewest tokens: https://www.anchorterminal.com/compare/microsoft-presidio-vs-shieldgemma.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "microsoft-presidio", "b": "shieldgemma"}`. From a terminal: `anchor compare microsoft-presidio shieldgemma`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/microsoft-presidio.json and https://www.anchorterminal.com/api/v1/tools/shieldgemma.json

## Other comparisons with Presidio or ShieldGemma

- [Amazon Bedrock Guardrails vs ShieldGemma](https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-shieldgemma.md)
- [Azure AI Content Safety (Prompt Shields) vs ShieldGemma](https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-shieldgemma.md)
- [Cisco AI Defense Inspection API vs ShieldGemma](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-shieldgemma.md)
- [Google Cloud Model Armor vs ShieldGemma](https://www.anchorterminal.com/compare/google-model-armor-vs-shieldgemma.md)
- [Granite Guardian vs ShieldGemma](https://www.anchorterminal.com/compare/granite-guardian-vs-shieldgemma.md)
- [Guardrails AI vs ShieldGemma](https://www.anchorterminal.com/compare/guardrails-ai-vs-shieldgemma.md)
- [Lakera Guard (Check Point AI Guardrails) vs ShieldGemma](https://www.anchorterminal.com/compare/lakera-guard-vs-shieldgemma.md)
- [Llama Guard 4 vs ShieldGemma](https://www.anchorterminal.com/compare/llama-guard-vs-shieldgemma.md)
- [Mistral Moderation API vs ShieldGemma](https://www.anchorterminal.com/compare/mistral-moderation-vs-shieldgemma.md)
- [NVIDIA NeMo Guardrails vs ShieldGemma](https://www.anchorterminal.com/compare/nemo-guardrails-vs-shieldgemma.md)
- [OpenAI Guardrails vs ShieldGemma](https://www.anchorterminal.com/compare/openai-guardrails-vs-shieldgemma.md)
- [OpenAI Moderation API vs ShieldGemma](https://www.anchorterminal.com/compare/openai-moderation-vs-shieldgemma.md)
- [Prisma AIRS AI Runtime Security API vs ShieldGemma](https://www.anchorterminal.com/compare/prisma-airs-vs-shieldgemma.md)
- [AgentGate vs ShieldGemma](https://www.anchorterminal.com/compare/agentgate-vs-shieldgemma.md)
- [LlamaFirewall vs ShieldGemma](https://www.anchorterminal.com/compare/llamafirewall-vs-shieldgemma.md)
- [Amazon Bedrock Guardrails vs Presidio](https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-microsoft-presidio.md)
- [Cisco AI Defense Inspection API vs Presidio](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-microsoft-presidio.md)
- [Google Cloud Model Armor vs Presidio](https://www.anchorterminal.com/compare/google-model-armor-vs-microsoft-presidio.md)
- [Guardrails AI vs Presidio](https://www.anchorterminal.com/compare/guardrails-ai-vs-microsoft-presidio.md)
- [Lakera Guard (Check Point AI Guardrails) vs Presidio](https://www.anchorterminal.com/compare/lakera-guard-vs-microsoft-presidio.md)
- [LlamaFirewall vs Presidio](https://www.anchorterminal.com/compare/llamafirewall-vs-microsoft-presidio.md)
- [Presidio vs Mistral Moderation API](https://www.anchorterminal.com/compare/microsoft-presidio-vs-mistral-moderation.md)
- [Presidio vs NVIDIA NeMo Guardrails](https://www.anchorterminal.com/compare/microsoft-presidio-vs-nemo-guardrails.md)
- [Presidio vs OpenAI Guardrails](https://www.anchorterminal.com/compare/microsoft-presidio-vs-openai-guardrails.md)
- [Presidio vs Prisma AIRS AI Runtime Security API](https://www.anchorterminal.com/compare/microsoft-presidio-vs-prisma-airs.md)
- [AgentGate vs Presidio](https://www.anchorterminal.com/compare/agentgate-vs-microsoft-presidio.md)
- [Granite Guardian vs Presidio](https://www.anchorterminal.com/compare/granite-guardian-vs-microsoft-presidio.md)
- [Llama Guard 4 vs Presidio](https://www.anchorterminal.com/compare/llama-guard-vs-microsoft-presidio.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp