Search

Frank brings order and helps you build complex LLM workflows using scalable, testable, and reusable components.

Network Storage API

A compositional semantic tokenizer for LLMs based on NSM primitives, emoji, and common word tokens

Minimalist and pragmatic static site generator, with an emphasis on blogging.

Severe Chronic Disease Pipeline

Benchmarking Llm Assisted Design and Evolution of algorithms.

A high-level Python web framework that encourages rapid development and clean, pragmatic design.

Detect contradictions between retrieved documents in RAG pipelines

AI-powered try/catch: explains unexpected errors and generates ready-to-paste fixes using OpenAI.

RAGAnything: All-in-One RAG System

LLM output validation with retry loops and optional Reflexion

A group of python modules for networking, plotting data, config storage, automating boot scripts, ssh access and user input output.

SKWhisper — Lumina's subconscious memory layer: digests Claude sessions, surfaces patterns, and writes whisper context

PDCA project management system for Feishu/Lark integration with AI-driven workflow

Universal intent router for Claude Code — one command that picks the highest-ROI skill automatically

Core engine for self-improving AI coding tool skills

A CLI tool for managing agent skills

Agent Store CLI

A KV cache management system that supports on-demand KV cache allocation for LLMs with GPU virtual memory

Guardrails for LangChain