Get an audit

Head to head · Guard pii · October 2026 research run

Presidio vs OpenAI Guardrails

OpenAI Guardrails scores 69.5 (B) on agent readiness against Presidio's 66 (B), and leads in 4 of 7 scored categories. Presidio leads on reliability. Both do guard pii.

PresidioData Privacy Stack · SDK + MCP B66/100#281 of 841 OpenAI GuardrailsOpenAI · Agent framework B69.5/100#175 of 841

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 73

Also in its favour

  • No key needed to call it

Watch for

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

OpenAI Guardrails B

Good for Teams already on the OpenAI client or Agents SDK that want several checks from one config file with little code.

Ahead on

  • Security & auth, 59 against 53
  • Maintenance & community, 89 against 63
  • Transparency & trust, 76 against 65

Watch for

By default a check that fails to run returns tripwire_triggered=False, so the request continues. Strict mode is opt-in

Score by category

CategoryWeight this runPresidioOpenAI GuardrailsEdge
Reliability16%207873Presidio +5
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26966Presidio +3
Agent ergonomics13%16.26973OpenAI Guardrails +4
Security & auth14%17.55359OpenAI Guardrails +6
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86389OpenAI Guardrails +26
Transparency & trust7%8.86576OpenAI Guardrails +11
Negative events≤1500
Total66 · B69.5 · B

Facts side by side

FactPresidioOpenAI Guardrails
KindSDK + MCPAgent framework
VendorData Privacy StackOpenAI
Hosted endpointno (local only)no (local only)
TransportsHTTPHTTP
AuthNoneAPI key
PricingFreeFree
x402nono
LicenceMITMIT
Read-only variant documentednono
llms.txtnono
Last release2026-07-222026-09-10
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Popularity11k stars, 1.2M PyPI/wk259 stars, 19k npm/wk, 105k PyPI/wk

Verdicts

Presidio

MIT-licensed personal data detector with a public OpenAPI document, tests on Python 3.10 to 3.14 and about 1.2 million weekly PyPI downloads. The REST containers have no authentication, the project states no SLA or support, and it covers personal data only, with no prompt injection or content moderation checks.

OpenAI Guardrails

MIT-licensed wrapper that adds twelve configurable checks to OpenAI client calls from one JSON file, with tool-level injection checks for the Agents SDK. The README labels it a preview at version 0.3.3, and by default a check that fails to run is reported as passed unless raise_guardrail_errors=True is set.

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. Download a spaCy model (python -m spacy download en_core_web_lg) before the first AnalyzerEngine() call, or use the Docker image
  3. Send both text and language to /analyze. A request missing either returns HTTP 500 with a JSON error field
  4. Pass entities and score_threshold to limit results. Many country-specific recognisers are disabled by default and need enabling in the registry YAML
  5. Keep the containers on a private network or behind your own authenticating proxy. They accept any caller

OpenAI Guardrails

  1. Pass raise_guardrail_errors=True to the client. The default treats a check that failed to run as passed
  2. Run python -m spacy download en_core_web_sm before using Contains PII, or client initialisation fails
  3. Catch GuardrailTripwireTriggered, and append a user message to history only after the call returns without it
  4. Use block=true for Contains PII in the output stage. Masking works only in the pre-flight stage
  5. Keep stream=False where output must be checked before it is shown, and budget one extra model call per LLM-based check

Questions

Which is better for AI agents, Presidio or OpenAI Guardrails?

OpenAI Guardrails scores 69.5 (B) on agent readiness against Presidio's 66 (B), and leads in 4 of 7 scored categories. Presidio leads on reliability.

Are Presidio and OpenAI Guardrails open source?

Yes. Presidio is open source (MIT). OpenAI Guardrails is open source (MIT).

Other comparisons with Presidio or OpenAI Guardrails

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report