All Stacks
Local AI
Local AI Stack
Run models locally, build on top of them, and keep your data entirely on-device: the privacy-first developer stack for open-source AI.
Our Take
Built for someone who wants inference and development entirely on their own hardware, a real requirement for data privacy or cost control, not a nice-to-have. LM Studio and Ollama both run local models, the difference is LM Studio's GUI versus Ollama's CLI-first, developer-friendly workflow, most people will settle on one after a week. This stack assumes a GPU capable of running models at usable speed, without that hardware the local-first premise doesn't hold and a cloud API is the more practical choice.
True Cost & Exit
What this stack really costs to run, and how you'd leave it.
Monthly cost
$0/mo (every tool in the stack runs free/open-source)
Lean alternative
This stack is already the lean alternative: every tool in it is free and open source, with your own hardware as the only real cost. Ollama alone, paired with its own CLI, covers running a local model if you want to trim even further.
Exit path
Every tool in this stack runs on your own machine, so your models, code, and data never leave local storage in the first place; there's no vendor account to export from because there's no vendor holding your data, the strongest exit posture of any stack in this catalog.
Tools in This Stack
Download, manage, and run large language models entirely on your own hardware, with a built-in chat interface and an OpenAI-compatible local server.
Run open-weight language models directly on your own machine with a single command, or shift to hosted GPUs via Ollama Cloud when local hardware isn't enough.
Run a self-hosted chat interface for local or API-based LLMs like Ollama behind your own login and controls, free at any scale if you keep default branding.
Use the existing open-source Continue codebase for configurable coding assistance in supported IDEs. Verify current hosted-service availability and support separately before adopting it for new work.
Run an AI coding agent inside your editor that reads and edits files, runs terminal commands, and executes multi-step development tasks with human approval at each step. Open source with 4.5M+ installs.