Use-case stack · teams, labs

RAG over internal docs

Stand up private Q&A over SOPs, BOMs, and handbooks for a lab or small team.

Docs must be curated. Garbage corpus → confident wrong answers. Prefer self-host when data is sensitive.

Preferred / primary

Self-hosted Automation

Self-hostable LLM app builder (RAG, agents, workflows) with a polished UI.

In this stack: Self-host RAG/agent portal for the team.

Details Site

Hybrid Research

Desktop/self-host RAG chat over your documents with multiple model backends.

In this stack: Desktop/self-host doc chat without greenfield ML.

Details Site

Self-hosted LLM / chat

Self-hosted ChatGPT-like UI over Ollama / OpenAI-compatible backends.

In this stack: When Ollama is already the lab standard.

Details Site

Web Research

Google’s source-grounded notebook for multi-doc Q&A and study guides.

In this stack: Fast grounded notebooks for smaller corpora.

Details Site

Self-hosted LLM / chat

Drop-in OpenAI-compatible gateway for local models (LLM, audio, image backends).

In this stack: OpenAI-compatible local gateway.

Details Site

Self-hosted LLM / chat

Simplest path to run open models locally (CLI + local API).

In this stack: Model backend.

Details Site

Hybrid Research

Local-first notes vault with optional AI plugins (cloud or local backends).

In this stack: Authoring environment for the corpus.

Details Site

Stacks are editorial starting points — swap tools when policy, budget, or hardware demands it.