Open-source chatbots that run entirely in your browser. A transformer embedding model, BM25 sparse retrieval, dense-sparse ensemble ranking, a 25-feature MLP policy network, and fragment-based composition — zero servers, zero LLMs, zero telemetry.
sentence-transformer (MiniLM-L6-v2) downloads once, caches in your browser, and runs fully on-device. A one-time warm-up — then it's yours forever.DecisionPacket — all locally.MLP policy network (13K parameters, RL-trained) determines mode, intent, topic count, creativity, and tone from your extracted features.On-device NLU assistant for Nash equilibrium, Shapley value, auctions, prisoner's dilemma, and more. Ask in natural language — get precise, mathematical answers with LaTeX rendering.
Launch ChatExplore the scientific and philosophical discoveries of the Islamic Golden Age. Ask about Al-Khwarizmi's algebra, Ibn al-Haytham's optics, the House of Wisdom, and the scholars who shaped modern science.
Launch ChatOn-device NLU assistant for data science and machine learning. Ask about pandas, NumPy, statistics, classification, regression, clustering, feature engineering, model evaluation, and more — all running locally in your browser.
Launch ChatReLU.chat is an open-source experiment by Yunus Emre Vurgun to discover simpler, faster ways to build chatbots — without creating an LLM or relying on pre-LLM era chatbot logic.
The goal is to combine sentence transformers, BM25 sparse retrieval, reinforcement-learned policy networks, and fragment-based composition into a system that runs entirely in the browser. No servers, no API keys, no data collection. The power stays on your device, achieving absolute data privacy for anyone who uses it.