← back to the directory
Library / SDK Retrieval & MemoryAgents & Orchestration

LLMWare

1Enterprise 2RAG 3framework 4using 5small 6models.

the six Ws · specification

W1 Who

By LLMWare.ai.

W2 What

A unified framework for RAG and agent pipelines using small, specialized models.

W3 Where

A Python library, runs locally or in cloud.

W4 When

When building private, cost-efficient RAG.

W5 Why

Enterprise RAG that runs on modest hardware.

W6 With

Python and optional local models.

W7 Watch

Apache-2.0 open-source; runs locally, models can be fully on-prem.

RAGEnterpriseSmall-models

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.