Search

Semantic caching framework for LLMs

OpenAI-compatible API proxy for Claude Max. Wraps Claude Code CLI — zero API keys needed.

Python SDK and window helper for ZekeGPT

From-scratch paged-attention inference engine: paged KV cache, continuous batching, preemption

Unified beverage knowledge hub — cocktails, wine, beer, whiskey, tea, coffee, and sake in one package.

Store Tryton files on Google Cloud Storage

Schema-driven Named Entity Recognition powered by local LLMs via Ollama

Local semantic search over your files — BM25 + embeddings (OpenAI or 100% offline via fastembed) with smart chunking, document extraction, and real-time file watching.

RAG Fallback Strategies - Intelligent fallback mechanisms for RAG systems

An integration package connecting VoyageAI and LangChain

CLI tool to transform photos into AI-generated re-imagined artwork via Claude and Gemini

Persistent associative memory system for Claude Code — complete development workflow

Template system for verification-first agentic development

Geometric region embeddings for knowledge graph subsumption (Python bindings for the subsume Rust crate)

This is a Python library for solving Hamilton-Jacobi-Bellman (HJB) equations using JAX. It provides a framework for numerical solutions to dynamic optimization problems in finance and economics.

A model-agnostic Python library with a unified API for multiple LLM providers

Package for LiteLLM Enterprise features

Lightweight drop-in Python decorator to track costs, monitor token usage, and enforce budget/rate limits for LLM API calls

Pack a folder into a single LLM-friendly context file

Pre/post-processing and analysis toolkit for ABINIT-MP Fragment Molecular Orbital calculations