Search

Chunking utilities for Donkit RagOps pipelines

Document loading helpers for Donkit RagOps

Create charts from FIO storage benchmark tool output

Ad network that delivers ads to the LLM's response

A unified, provider-agnostic Python client for multiple LLM APIs

A powerful Python toolkit for simplifying LLM integration and management with multi-model scheduling, fault tolerance, and load balancing support

The AI native context-aware semantic cache for LLM apps — stop paying for the same answer twice

Build and maintain Obsidian knowledge bases with LLM assistance

Library for managing DSW S3 storage

MCard: Local-first Content Addressable Storage with Content Type Detection

Self-learning RAG field prediction SDK for PDF form filling.

Framework designed to simplify and accelerate the development of LLM-based applications.

A Python package for explaining RAG pipelines.

"A set of interop services to integrate and transfer data between different applications, model and storage technologies for the bclearer framework."

Python package to allow easy integration to Neo4j's GraphRAG features

Django cache management with fragmented keys for better invalidation support

Neurotransmitter-inspired adaptive learning layer for LLMs

Cartridge that provides fast, scalable, and efficient storage and searching solution for chemical information using Elasticsearch

A htop-like TUI for monitoring Claude Code sessions in real-time

AI-powered code review loop — automates Codex review + Claude fix cycles