llm training and inference in C++ & python with web UI train and run Models locally

A pure Elixir Datalog engine with semi-naive fixpoint evaluation, stratified negation, provenance tracking, and telemetry.

Совместный проект курса в МФТИ по методам эффективной реализации моделей искусственного интеллекта

Fast, dependency-free LLM engine in Rust with custom SIMD kernels

Nectar-X-Studio is a powerful, Local AI-Inferencing application that allows the user download, create, run agents and run large language models on their own machine. With no internet connection required, Nectar ensures privacy-first, high-performance inference using cutting-edge open-source models from Hugging Face, Ollama, and beyond.

Rust SDK for writing custom backends for NVIDIA Triton Inference Server

Local-first LLM toolkit: token/KV-cache/VRAM analyzer, Ollama paraphrase pipeline, and a weighted load-balancer with health checks. 100% local — no API keys, no data leaves your machine. 51 passing tests.

Duplex is an advanced, strictly client-side application designed to interface with multiple Large Language Models simultaneously. Run local instances through Ollama and multiple cloud APIs in a unified, privacy-first interface.