Stacks
Find the right AI stack recipe.
Stack recipes are tested combinations of model, runtime, and interface that work together — a proven starting point instead of assembling one from scratch. Search stack recipes for local AI, private chat, coding assistants, RAG, automation, MCP agents, and home labs.
Editorial-first — instructions preserved as written and tested
Tested recipes
Each stack recipe documents the tools, hardware, and time investment before you start.
Start small
Quickstart recipes are ordered from beginner to intermediate so you add complexity one layer at a time.
Decision-focused filters
Narrow by local AI, coding, RAG, agents, or automation before comparing recipes.
Quickstart recipes
Three paths from zero to running model
Beginner
Ollama Quickstart
- Best for
- First local model — no prior AI experience needed
- Hardware
- 8 GB RAM min · 8 GB VRAM recommended
- Tools
- Ollama · Open WebUI
- Time
- 5–10 minutes
Developer · No Docker
llama.cpp GGUF Workflow
- Best for
- Running any GGUF file without a runtime abstraction layer
- Hardware
- 8 GB RAM · CPU-only possible
- Tools
- llama.cpp · Hugging Face GGUF hub
- Time
- 15–30 minutes
RAG · Intermediate
Local RAG with Qdrant
- Best for
- Searching private documents with fully local models
- Hardware
- 16 GB RAM · any GPU or CPU
- Tools
- Ollama · Qdrant · Open WebUI
- Time
- 20–30 minutes
Recipe matrix
All stack recipes by use case
Agentic Workspace Stack
Local-first multi-agent framework utilizing specialized open-weight reasoning and tool-calling models.
View recipe →AI Automation Workflow Stack
A workflow automation stack for turning AI outputs into drafts, approvals, notifications, and controlled actions.
View recipe →Edge and Low-Power AI Stack
A minimal always-on inference setup for sub-4B models on Raspberry Pi 5, ARM SBCs, Intel NUCs, or embedded appliances with 8–16 GB RAM and no discrete GPU.
View recipe →Enterprise RAG Stack with Access Control
A production RAG setup combining Qdrant, LlamaIndex, and a local LLM behind an authentication and role-based access control layer — for regulated enterprise environments.
View recipe →GPU Cloud Fine-Tuning Stack
A stack for fine-tuning or running large models on rented GPU cloud infrastructure without owning the hardware.
View recipe →Home Lab AI Stack
A home-lab stack for local inference, private chat, and optional smart-home integrations.
View recipe →Lightweight Laptop AI Stack
A minimal stack for running small local models on a laptop or low-VRAM machine without a dedicated GPU.
View recipe →Local Coding Agent with Persistent Memory
A coding agent stack that retains project context across sessions using local memory storage — giving the model awareness of conventions, past decisions, and ongoing work without restarting from scratch.
View recipe →Local Coding Assistant Stack
A coding stack for testing open coding assistants with local or self-hosted models, repository-aware tools, and human code review.
View recipe →Local Multi-Modal Vision Stack
A local stack for image understanding, visual Q&A, and document image analysis using vision-capable open models running fully on your hardware.
View recipe →MCP Agent Workflow Stack
A starter stack for connecting coding agents to approved tools through MCP servers.
View recipe →Private Document RAG Stack
A local RAG setup for indexing internal documents with a vector store, a model runner, and a chat UI.
View recipe →Private Local Chatbot Stack
A practical stack for running private chat over local or self-hosted models with a browser chat UI and clear review habits.
View recipe →Private Sovereign Knowledge Base
Air-gapped text extraction and semantic search cluster for processing confidential enterprise documents.
View recipe →Voice AI Assistant Stack
A voice-in, voice-out AI pipeline combining Whisper for transcription, a local LLM for reasoning, and ElevenLabs or Coqui TTS for speech synthesis — no cloud transcription required.
View recipe →Showing 15 of 15 stacks.
Stack recipe
Agentic Workspace Stack
Local-first multi-agent framework utilizing specialized open-weight reasoning and tool-calling models.
View stack →Stack recipe
AI Automation Workflow Stack
A workflow automation stack for turning AI outputs into drafts, approvals, notifications, and controlled actions.
View stack →Stack recipe
Edge and Low-Power AI Stack
A minimal always-on inference setup for sub-4B models on Raspberry Pi 5, ARM SBCs, Intel NUCs, or embedded appliances with 8–16 GB RAM and no discrete GPU.
View stack →Stack recipe
Enterprise RAG Stack with Access Control
A production RAG setup combining Qdrant, LlamaIndex, and a local LLM behind an authentication and role-based access control layer — for regulated enterprise environments.
View stack →Stack recipe
GPU Cloud Fine-Tuning Stack
A stack for fine-tuning or running large models on rented GPU cloud infrastructure without owning the hardware.
View stack →Stack recipe
Home Lab AI Stack
A home-lab stack for local inference, private chat, and optional smart-home integrations.
View stack →Stack recipe
Lightweight Laptop AI Stack
A minimal stack for running small local models on a laptop or low-VRAM machine without a dedicated GPU.
View stack →Stack recipe
Local Coding Agent with Persistent Memory
A coding agent stack that retains project context across sessions using local memory storage — giving the model awareness of conventions, past decisions, and ongoing work without restarting from scratch.
View stack →Stack recipe
Local Coding Assistant Stack
A coding stack for testing open coding assistants with local or self-hosted models, repository-aware tools, and human code review.
View stack →Stack recipe
Local Multi-Modal Vision Stack
A local stack for image understanding, visual Q&A, and document image analysis using vision-capable open models running fully on your hardware.
View stack →Stack recipe
MCP Agent Workflow Stack
A starter stack for connecting coding agents to approved tools through MCP servers.
View stack →Stack recipe
Private Document RAG Stack
A local RAG setup for indexing internal documents with a vector store, a model runner, and a chat UI.
View stack →Stack recipe
Private Local Chatbot Stack
A practical stack for running private chat over local or self-hosted models with a browser chat UI and clear review habits.
View stack →Stack recipe
Private Sovereign Knowledge Base
Air-gapped text extraction and semantic search cluster for processing confidential enterprise documents.
View stack →Stack recipe
Voice AI Assistant Stack
A voice-in, voice-out AI pipeline combining Whisper for transcription, a local LLM for reasoning, and ElevenLabs or Coqui TTS for speech synthesis — no cloud transcription required.
View stack →Useful starting points
Next step
Test and then build.
Use the Playground and compatibility checker before settling on a stack.
For builders
Have a practical AI stack to share?
Submit a tool, model, or workflow for editorial review, or sponsor a clearly labeled placement. For sponsorship options, advertise with us. For submissions or corrections, use the submit page.