The complete Atlas Stack: every component, documented and wired, plus a live
session to get it running on your hardware.

WHAT YOU GET

All sixteen components:

INFERENCE
Ollama, llama.cpp, Hugging Face TGI, vLLM, LocalAI

VECTOR SEARCH
Qdrant, Chroma, Milvus, FAISS

RAG & AGENTS
LlamaIndex, LangChain, Haystack, CrewAI

DEVELOPER TOOLS
Aider, Semantic Kernel, Continue

Plus:

• A Compose stack definition covering the services
• Environment template with pinned tags
• verify.sh health check across the stack
• Per-component docs explaining role and trade-offs
• RUNBOOK.md operations guide
• fetch-sources.sh pinned to exact commits
• Full attribution for every project

1:1 ONBOARDING SESSION
A live session to walk through the components relevant to your stack, help
wire them into your existing infrastructure, and answer your specific setup
questions - so it is integrated properly the first time.

LIFETIME UPDATES
Every future improvement to this bundle, at no extra cost.

ALL OPEN SOURCE, ALL PERMISSIVE

MIT and Apache-2.0 throughout. The value here is the integration, the
documentation, the operational runbooks and the session - the upstream source
is freely available and this bundle tells you exactly where and how to get it.

REQUIREMENTS

Docker Engine 24+ with Compose v2. GPU strongly recommended for vLLM and TGI.

One-time purchase. Code, updates and support access are yours; the onboarding
session is scheduled after purchase.