Bundle: Lab Kit + Starter Pack

What you get

The bundle is both kits below, each exactly as described on its own product page. Each kit keeps its own licence unchanged; buying the bundle does not change either licence.

1. Self-Hosted AI Lab Kit — $19 bought separately

Self-Hosted AI Lab Kit: stop guessing which local model fits your machine. A ready-to-use lab notebook — in Excel and Notion — for testing, comparing and running AI on your own hardware, without the spreadsheet setup.

Self-Hosted AI Lab Kit workbook cover preview — Preview made from a real screenshot of the actual workbook, with a clean title overlay — no fake UI was invented.

Model Library — pre-filled with 6 well-known local models, with parameters, quantisation, licence and the publisher's own model-card source for every fact. Starter ratings are clearly marked as opinion, not benchmarks.
Hardware Profile & VRAM Estimator — type in your GPU and a model size, and get an estimated fit, with the formula shown in plain sight. Labelled as an estimate throughout — because real performance depends on your engine, context and drivers.
Prompt Log & Test Results — log the same prompt across models, with tokens/sec calculated automatically.
Deployment Checklist — install, hardening, backup and update steps, so your local server is not accidentally open to the internet.
Cost Tracker — electricity, GPU/cloud hours and API fallback, plus a local-vs-API saving formula.
Experiment Tracker — change one thing at a time, score it 1–10, and actually know what caused the improvement.
Dashboard with charts — totals, averages and monthly cost by category, all by formula.
Notion version included — a Markdown home page plus 6 importable CSV databases.
No macros, no tracking, works in Excel and Google Sheets.

Also included in the Lab Kit

30-item Hardening & Backup Checklist (PDF) — printable, tick-box checklist covering install, network hardening, keys & data, backup and updates.
20 Prompt Templates for Local-Model Evaluation (original) — summarising, code, reasoning, RAG, JSON extraction, hallucination resistance and more, each with suggested settings and pass criteria. Run them yourself; no results are pre-filled.

2. Private AI Starter Pack — $29 bought separately

Private AI Starter Pack Bundle: your own ChatGPT-style assistant, over your own documents, on your own machine. No monthly AI subscription.

AnythingLLM workspace chat answering the sample question — Screenshot from this kit's own test run (AnythingLLM 1.19.0): workspace chat answering the sample question, with sample-guide.txt cited as the source. The AnythingLLM interface is part of AnythingLLM (MIT, Mintplex Labs).

A ready-to-run Docker Compose stack (local PC profile + VPS profile with HTTPS via Caddy and basic auth), with pinned, verified versions: Ollama 0.40.13, AnythingLLM 1.19.0, and Caddy 2.11.7-alpine for the VPS profile.
One-command installers for Linux/macOS and Windows, plus backup, restore and update scripts — all idempotent, no telemetry added.
A PDF guide: requirements, setup for both profiles, adding documents, choosing models, security hardening, backup and restore, troubleshooting with real error messages, and FAQ.
A sample document with a test question, so you can prove document Q&A works in ten minutes.
Third-party licences and attribution, and a plain-English buyer licence.

Before you buy — Starter Pack requirements and testing note

The Lab Kit's VRAM figures are estimates from a stated formula, not guarantees. Always test with your real setup.

Starter Pack requirements: Docker + Docker Compose v2 (Docker Desktop on Windows/Mac); local CPU: 8 GB RAM minimum (default 3B model), 16 GB for 7–8B models, ~10 GB free disk; optional GPU: NVIDIA GPU + NVIDIA Container Toolkit; VPS: 2 vCPU, 8 GB RAM, a domain name, ports 80/443 open; internet for the first download only.

What was actually tested for the Starter Pack (v1.0.1, 30 October 2026, Linux VM): the local CPU install, both containers healthy (Ollama 0.40.13, AnythingLLM 1.19.0), a small chat model and nomic-embed-text pulled, the sample document embedded, and the sample question answered from that file, with a citation. Backup, restore and update were run and passed. The test used qwen2.5:0.5b, not the default model. The kit default in .env.example is still llama3.2:3b. That default model was not downloaded or run in the test.

Not tested for the Starter Pack: Windows, macOS, NVIDIA GPU, a real domain with TLS (the VPS/Caddy profile), and the default 3B model, llama3.2:3b. Read the full honest testing note on the Private AI Starter Pack page before you buy.

Licences — each kit keeps its own

Self-Hosted AI Lab Kit — LICENSE.md: personal use and commercial use in your own work and projects are allowed. Fill it in, adapt the blank rows and templates to your lab, and keep your filled-in copy. Not allowed: reselling, redistributing, sharing publicly, or giving away the kit itself, in whole or in part, in its original or lightly modified form. The free Lite version may be shared freely for community distribution, as provided, without modification to its contents or licence note. Models and tools named in the kit have separate licences that belong to their publishers; this kit's licence does not grant any rights to those models or tools.

Private AI Starter Pack — LICENSE-KIT.md plus third-party licences: personal and commercial use of the kit is allowed. You may modify the configuration and scripts for your own use. You may not redistribute, resell, share, publish, upload, or give away the kit itself, in whole or in part, free or paid. Do not remove attribution or licence notices, and do not claim you wrote Ollama, AnythingLLM, or Caddy, or that this kit is an official product of those projects. It is not. The kit is provided “as is”, without warranty. Installing it for a client as part of a paid setup service is allowed only as LICENSE-KIT.md states: the client must receive their own licensed copy of the kit, or you must keep the kit files out of what you hand over.

You pay for the kits and guides, not for the open-source software. Ollama is MIT, AnythingLLM is MIT, and Caddy is Apache-2.0. Nothing in either kit charges you for them, and nothing in either kit transfers ownership of them to you. Models are separate: the Starter Pack's default chat model, llama3.2:3b, is a Meta Llama model under Meta's Llama Community License, not MIT, and the embedding model, nomic-embed-text, and any other model you choose each have their own licence — check it before commercial use. This summary is attribution, not legal advice; the project licence governs your use of that software.

Questions

Do I get both kits?

Yes — both downloads, each as described on its own product page, each under its own licence above.

Can I buy the kits separately instead?

Yes: the Self-Hosted AI Lab Kit is $19 and the Private AI Starter Pack Bundle is $29. Together they are $48; the bundle is $39.

Do I pay for Ollama or AnythingLLM?

No. They are free, open-source software (both MIT). You pay for the kits and guides only. See the third-party licences above.

Is a setup service included?

No. Delivery is an instant digital download after purchase; no setup service is included.

Purchase details

Seller: StackGuide AI. Price: $39. Refund policy: Refunds are available within 3 days of purchase only if a file is corrupted or the product materially does not match its description. Buyers should first email [email protected] so we can send a fixed file. — see the refund policy. Creem is the merchant of record and handles payment and tax. Delivery is an instant digital download after purchase; no setup service is included. Questions: [email protected]. Also available separately: the Self-Hosted AI Lab Kit ($19) and the Private AI Starter Pack Bundle ($29).