Researching the next layer of intelligence.

We turn frontier AI into dependable systems, models, agents, and safety layers designed for production.

We build AI that solves vertical problems end-to-end: proprietary models, deterministic safety layers, and production-grade evaluation.

Research

Yeco Flash Mini-IT v1

118M-parameter Italian micro-LLM, trained for under €15, ~200 tok/s on CPU. Beats 5× larger models on Italian logic benchmarks.

A heavily optimized fine-tune of Qwen2.5-Coder-3B on EnderDevelopment data. Internal to EnderDevelopment only: no open weights, no public API. Staged rollout: Premium first, then new free users, then everyone.

Yeco-PII v1.0

Proprietary 278M model. Beats Rizzo-PII (0.3B) and OpenAI Privacy Filter (1.5B) on all 6 European languages, average F1 0.97 vs 0.77 vs 0.71.

From Standard Italian to Dialects: Early Experiments with Napoletano-Ciro and Piemontese-Gioan

Two LoRA adapters on Qwen2.5-1.5B-Instruct, one for Neapolitan and one for Piedmontese, built as open conversational experiments by YecoAI Research. They are early, experimental releases and are not part of the Yeco LLM Series.

Products

DeskNexo

DeskNexo is the AI support agent for hosting providers: it reads WHMCS tickets, diagnoses VMs on Proxmox and VirtFusion, resolves the issue, and writes a human reply to your customer, alone, in under 30 seconds, 24/7. Every action is snapshot-protected and dual-LLM verified.

EnderDevelopment

EnderDevelopment is the AI platform for gaming communities: natural language in, working Minecraft plugins (Spigot/Paper), FiveM scripts, Discord bots and server configs out. Free plan, credit-based pricing from €8/month, and the real-world training ground for Ender-1.

Yeco LLM Series

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.

Our latest news

See all

YecoAI Joins Claude Startups

YecoAI is accepted into Anthropic's Claude Startups program: one year of Claude Team free and over $1,000 in Claude API credits. For us, that support is huge.

YecoAI Wins the Premio Aulab and Third Place at DigithON 2026

Two awards in one weekend: YecoAI takes home the Premio Aulab and finishes third at DigithON 2026. A heartfelt thank you to DigithON, Aulab, and everyone who believed in us.

New Brand and Website: Live Today

Twenty days of redesign, from August 10 to September 30, 2026. The new YecoAI brand and official website are live, designed by Kevin Paratore of IdraArts.

Yeco Flash Mini-IT: an Italian Micro-LLM Trained for Under €15

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 Enters Beta: Our Proprietary 3B Model Trained on EnderDevelopment Data

Ender-1 is our proprietary 3B model trained on EnderDevelopment data (free users, policy-compliant). In beta: staged rollout beginning in shadow mode.