ai-ml

Persistent, emotionally-weighted memory for any LLM

High-performance Rust-based inference gateway for large-scale LLM deployments

A client library for LoLLMs generate endpoint

The main objective of this package is to centralize logic used to interact with Azure Functions, Azure Service Bus and Azure Table Storage

DlightRAG - Dual-mode multi-modal RAG service based on LightRAG

Official Python SDK for Variably feature flags, LLM experimentation, and prompt optimization platform

LiteLLM provider for exoclaw

Terminal UI for managing Claude Code sessions, projects, and data

Development workflow toolkit for Claude Code with issue management, code quality commands, and automated processing

LLM and VLM model

A modern RAG ingestion pipeline from Nvidia

az-scout plugin for On-Demand Capacity Reservation (ODCR) coverage analysis

Claude Automatic Optimizer — wraps PyTorch optimizers and consults Claude to tune hyperparameters

Geometric OOD detection for LLM hidden states

Production-ready Telegram FAQ bot with Russian LLMs, RAG, and multi-provider fallback

Portable Claude Code workspace archives

A Python package for tuning vLLM hyperparameters.

Self-hosted semantic search and knowledge management for LLM-driven development

Atomic Model Fragmentation (AMF) - Universal LLM Decomposition Library

Backend.AI Storage Proxy