Vincent Sanicolas

A high-performance incremental JSON stream parsing library published across the TypeScript (NPM) and Dart (pub.dev) ecosystems. Engineered with an event-driven state machine to intercept, buffer, and incrementally parse incomplete, chunked LLM JSON outputs, enabling real-time generative UI assembly and instant data bindings before the stream terminates.

A comprehensive, multi-language streaming parsing engine compiled for Python, TypeScript, Dart, C#, and Kotlin. Specially designed to handle real-time structural analysis of incomplete, tokenized data packets, incrementally yielding valid syntactic sub-trees from raw JSON, YAML, and XML model streams as they are emitted byte-by-byte.

A full-stack, AI-augmented educational platform utilizing a custom Free Spaced Repetition Scheduler (FSRS) algorithm and local vector embeddings. Built with Flutter, Supabase, and PostgreSQL, the engine indexes textbook PDFs locally to build context-aware active recall pipelines, automatically generating high-yield study decks and quizzes without data hallucination.

An experimental dynamic canvas framework that compiles natural language prompts into fully functional native applications at runtime, bypassing traditional compilation steps. Engineered complete with an on-the-fly local database, reactive state management, runtime scripting execution, dynamic native layouts, and an integrated AI architect capable of designing, building, and running the entire system interactively.

A highly modular, event-driven generative UI layout engine for Flutter applications. Designed to decouple AI transport layers from front-end widget trees, it handles namespaced token streams, compiles partial JSON component schemas via reactive builders, manages multi-view target-routing tags, and dynamically activates passive inputs as streams finalize.