ai-ml

Async-native Python framework for building production-grade LLM applications. Streaming-first, 2 dependencies, fully transparent.

A library containing components related to model inferences in Gen AI applications.

A Python library encapsulating best practices for rubric-based evaluation of LLM/VLM outputs using LLM-as-a-judge.

A human-like LLM memory system.

The way to build RAG — modular, configurable, plugin-based

🌿SeaweedFS is a fast distributed storage system for blobs, objects, files, and data lake, for billions of files! Blob store has O(1) disk seek, cloud tiering.

Library for building prompts for LLMs

Auto-redirect LLM API requests (OpenAI, Anthropic, Gemini, Mistral, Cohere, OpenRouter) to xAI APIs - Just Grok It!

Flexible taxonomy management for generic items — categories, tags, and multi-parent hierarchies with pluggable storage.

Deterministic conversational state engine for LLM applications.

Runtime Reliability Infrastructure for LLM Pipelines

Interactive canvas widget for CustomTkinter with draggable, resizable rectangles

OpenRouter-compatible LLM router with unified batch support. Route requests across OpenAI, Anthropic, and Google with a single API.

CIPHER — Security Engineering Assistant with RAG-powered knowledge base

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