On Premise Python Packages

hexaswarm-core

Universal primitives for Claude-native multi-agent software delivery — orchestrator, cost tracker, safety, stack adapters, and the `hexa` CLI.

zettabrain-rag

Private AI document assistant — chat with your documents using a fully local RAG pipeline. No API keys, no cloud, no data leaving your machine.

mcp-devops-onpremise

The MCP server for Azure DevOps On-Premise (TFS), connecting your agents with DevOps capabilities.

latence-solver

High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU kernels, ROQ quantization, LEMUR routing, WAL-backed CRUD, and a FastAPI server — single machine, CPU or GPU.

voyager-index

High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU kernels, ROQ quantization, LEMUR routing, WAL-backed CRUD, and a FastAPI server — single machine, CPU or GPU.

autocore

A Python library that unifies GUI automation, headless browser control and common system actions into a single import.

llama-client-aic

python client for redten - a platform for building and testing distributed, self-hosted LLMs with native RAG and Reinforcement Learning with Human Feedback (RLHF) https://api.redten.io

aws-cdk-serverbluegreendeploymentgroup

AWS CDK's construct for creating a CodeDeploy Deployment Group with Blue/Green deployment configuration for EC2/On-Premises servers. It enables controlled traffic switching between old and new instances, automatic rollback on failure, and more.

openark

OpenARK Python Client

autodist

Simple Distributed Deep Learning on TensorFlow

colsearch

High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU kernels, ROQ quantization, LEMUR routing, WAL-backed CRUD, and a FastAPI server — single machine, CPU or GPU.