FlowX.AI

Open, on-device AI for regulated industries. We build small, private, fast models that run on-premise with zero data egress, so banks, insurers, and logistics operators can use AI without sending customer data to a cloud.

🧠 OpenNER — small on-device extraction models

28 fine-tuned encoder models for structured extraction, PII detection, and de-identification. Apache-2.0. Benchmarked against the latest frontier LLMs (GPT-5.4, Gemini 3.x, Claude Haiku): matching or beating them on structured extraction at ~100 ms/doc, $0, and zero data egress.

• 🏦 FlowX Banking Models — IBAN/PAN/KYC/AML + SEC-filing facts (8 models)
• 🛡️ FlowX Insurance Models — policy/claims/VIN + GLBA·HIPAA de-id (8 models)
• 🚢 FlowX Logistics Models — container/port/hazmat/bill-of-lading + trade de-id (7 models)
• 🌐 FlowX Cross-Industry Models — multilingual PII (9 languages), privacy filter, invoice/CV/KYB (5 models)

Every identifier is checksum-validated (IBAN mod-97, card Luhn, ISIN/LEI, container ISO-6346, VIN, 8 national IDs). Ships with a de-identification engine (6 policy profiles + signed audit reports) and ONNX / INT8 edge exports. Runs on CPU, Apple Silicon, one GPU, or in the browser.

Other model families

• Semantic Mapper · Sentinel Gate — ontology extraction + escalation gating
• Scam Guard — scam / fraud detection
• BPMN Gen — business-process generation

Small models, on your hardware. Apache-2.0. flowx.ai