Yeco-PII v1.0 is a 278M-parameter neural model that detects and anonymizes personal data (PII) in business documents — native Italian, certified on 6 European languages, average F1 0.966, beating models 5.4× its size. Enterprise API trial available; one-time license, on-prem delivery.
Yeco-PII v1.0 is a proprietary neural PII detection and anonymization model for companies that process sensitive documents: hosting providers, healthcare organizations, and banks. It understands personal data from context — including names it has never seen during training — without regex, manual rules, or validation formulas. On identical third-party benchmarks (Ai4Privacy), it beats OpenAI's Privacy Filter on all 6 European languages with an average F1 of 0.966 vs 0.769, using 5.4× fewer parameters (278M vs 1.5B).
DeskNexo is an AI support agent that reads, diagnoses, and resolves WHMCS hosting tickets in under 30 seconds — connected natively to WHMCS, Proxmox, and VirtFusion. Every answer is verified by a second AI judge before it reaches the customer. 20K active users on the underlying platform.
EnderDevelopment is the AI-powered platform that turns natural-language requests into production-ready Minecraft plugins (Spigot/Paper), FiveM scripts, Discord bots, and server configs. 20K active users, 80K prompts generated, 100% organic growth — and the real-world training ground for Ender-1.
Yeco LLM Series is YecoAI's family of proprietary Italian AI models: Yeco-PII v1.0 (278M, privacy), Ender-1 (3B, gaming, beta) and Yeco Flash Mini-IT v1 (118M, trained for under €15). Sovereign, efficient, compliance-ready — this page is updated as the series grows.
118M parameters, trained for under €15, ~200 tok/s on a consumer CPU. Yeco Flash Mini-IT is our proof of concept that sovereignty beats scale.
Ender-1 is our proprietary 3B model trained on EnderDevelopment data (free users, policy-compliant). In beta: staged rollout beginning in shadow mode.
278M-parameter neural model for PII detection and anonymization. Native Italian, 6 European languages, average F1 0.966.
YecoAI publishes its position on the EU AI Act: full compliance with transparency obligations, with technical concerns on high-risk evaluation requirements.
YecoAI reaches the DigithON 2026 finals — recognition for its applied AI research and product portfolio.
YECOAI di Marco Nasi has been awarded a non-repayable contribution of €18,200 under the ACN program promoted by Invitalia.