Get an audit

Head to head · Guard pii · October 2026 research run

LlamaFirewall vs Presidio

Presidio scores 66 (B) on agent readiness against LlamaFirewall's 50.8 (D), and leads in 6 of 7 scored categories. Both do guard pii.

LlamaFirewallMeta · Agent framework D50.8/100#682 of 841 PresidioData Privacy Stack · SDK + MCP B66/100#281 of 841

Which one, for what

LlamaFirewall D

Good for A Python agent team that wants injection, hidden-character and generated-code checks in process, is willing to pin dependencies or install from main, and can get the gated weights.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No PyPI release since 1.0.3 on 29 May 2025, and no changelog, tags or deprecation notes were found

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 53
  • Schema & documentation, 69 against 49
  • Agent ergonomics, 69 against 60
  • Payments & pricing, 60 against 50
  • Maintenance & community, 63 against 15
  • Transparency & trust, 65 against 58

Watch for

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

Score by category

CategoryWeight this runLlamaFirewallPresidioEdge
Reliability16%205378Presidio +25
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.24969Presidio +20
Agent ergonomics13%16.26069Presidio +9
Security & auth14%17.55653LlamaFirewall +3
Payments & pricing10%12.55060Presidio +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.81563Presidio +48
Transparency & trust7%8.85865Presidio +7
Negative events≤1500
Total50.8 · D66 · B

Facts side by side

FactLlamaFirewallPresidio
KindAgent frameworkSDK + MCP
VendorMetaData Privacy Stack
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthNoneNone
PricingFreeFree
x402nono
LicenceMIT (library). The Prompt Guard 2 weights it downloads are under the Llama 4 Community LicenceMIT
Read-only variant documentednono
llms.txtnono
Last release2025-05-292026-07-22
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
Popularity4.4k stars, 1k PyPI/wk11k stars, 1.2M PyPI/wk

Verdicts

LlamaFirewall

One scan() call runs several checks on the owner's machine and returns a short typed result. The last PyPI release is 1.0.3 from 29 May 2025, and its Prompt Guard loader imports a huggingface_hub class that current versions no longer export, so a fresh install needs older pins. The classifier weights also need Meta's manual approval.

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.

Before you call either

LlamaFirewall

  1. Pin huggingface_hub below 1.0 and a matching transformers 4.x before importing the Prompt Guard scanner from the 1.0.3 wheel, or install from main
  2. Get access to meta-llama/Llama-Prompt-Guard-2-86M and set a Hugging Face token first. Without one the loader prompts for a login and a headless run stalls
  3. Call scan_async inside a running event loop. scan() wraps asyncio.run and fails there. scan_async returns score 0.0 and reason default on every allow
  4. Split text longer than 512 tokens yourself before a Prompt Guard scan. The library truncates and does not chunk
  5. Do not feed a block reason back to the model. The Prompt Guard reason quotes the full scanned text, and the hidden ASCII reason decodes the hidden payload

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

Questions

Which is better for AI agents, LlamaFirewall or Presidio?

Presidio scores 66 (B) on agent readiness against LlamaFirewall's 50.8 (D), and leads in 6 of 7 scored categories.

Are LlamaFirewall and Presidio open source?

Yes. LlamaFirewall is open source (MIT (library). The Prompt Guard 2 weights it downloads are under the Llama 4 Community Licence). Presidio is open source (MIT).

Other comparisons with LlamaFirewall or Presidio

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