OpenSecureAI Prompt Firewall vs PII Firewall
OpenSecureAI Prompt Firewall
opensecureai.comPII Firewall
pii-firewall.comSide by side
| Figure | OpenSecureAI Prompt Firewall | PII Firewall |
|---|---|---|
| Price from | $49/mo | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | — |
| Linux | — | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 3 | 1 |
| Spec score · AI Guardrail Software | 8.1 (#5) | 7.2 (#18) |
| Detection | It combines prompt-injection detection, secret detection, and PII redaction under a user-controlled policy. | Detection backends include regex, Presidio, GLiNER, Transformers, OpenAI Privacy Filter, hybrid, and custom options. |
| Purpose | Prompt Firewall decides whether text is allowed, flagged, or blocked before it reaches an LLM. | Intercepts and anonymizes PII before it reaches an LLM, then restores original values in the response. |
Plans
OpenSecureAI Prompt Firewall
- FreeFree
- Pro$49 a month
- TeamPriced on request
In their own words
OpenSecureAI Prompt Firewall
OpenSecureAI Prompt Firewall evaluates text before it reaches an LLM and applies a policy to allow, flag, or block it. Separate engines check for prompt injection and for PII or secrets. Under the described policy, injection or secrets trigger a block, while PII is redacted and flagged. The same middleware logic can be applied to model inputs and outputs. The live demonstration runs client-side and states that nothing is uploaded. Developers can use the open-source, dependency-free core as an npm package or CLI for applications and CI. The CLI reads files or standard input and can return a nonzero exit code when findings reach a selected threshold. An API key unlocks hosted detections for additional risks, including obfuscation or encoding evasions, indirect injection, tool abuse, and multilingual overrides. The LLM Gateway supports OpenAI, Anthropic, xAI, and Groq with bring-your-own-key operation; the company says gateway provider keys are never stored or logged. The Free plan is free and includes 2,000 API requests per month. Pro costs $49 a month and includes 50,000 monthly requests.
PII Firewall
PII Firewall is an open-source, self-hosted tool that intercepts personally identifiable information before it reaches an LLM, then restores original values in the response. The maker highlights healthcare, finance, and legal workflows, including clinical language processing, fintech support automation, and legal document review. Built-in profiles cover healthcare, finance, legal, and generic use, with custom profiles also available.
Detection options include regex, Presidio, GLiNER, Transformers, OpenAI Privacy Filter, hybrid setups, and custom backends. Users can choose to keep, pseudonymize, redact, generalize, mask, or hash detected information. The product says it supports 55+ languages with automatic language detection and locale-specific patterns. Integration examples include OpenAI, Anthropic, LangChain, FastAPI, streaming transport, Ollama, LiteLLM, and arbitrary HTTP LLM endpoints. Tenant-scoped token mappings and a forget operation support deleting vault mappings for a thread or case. Each call produces a trace with detected entity types, confidence scores, and replacements. The project uses the Apache 2.0 license and provides a Python package; its regex-only base install does not require ML dependencies. The maker says hash is for analytics workflows and is not used in built-in presets.