Local AI
Open-weight and open-source models and the tools that run them, tested on our own machine: how fast they run, how much memory they need, what they send home and what they cost to run against paying for a cloud service.
Builds & ToolsDemucs and WhisperX: A Local Audio Cleanup Pipeline
A build log for our interview chain: Demucs isolates a voice from a noisy field recording, WhisperX transcribes it with…
Builds & ToolsComfyUI Workflow: A Fully Local Image Pipeline
A ComfyUI workflow that runs entirely on one Mac: a node graph instead of a prompt box, models kept on…
Behind-the-scenesHow to Evaluate Open-Source AI Tools: The Atlas Method
A look inside the Atlas, our running record of every local AI tool we test. The same template for every…
Builds & ToolsWiring OpenCode to a Local Model: A Build Walkthrough
An OpenCode local model walkthrough, not a brochure. We wired a coding agent to a model on our own machine…
AnalysisThe Hidden Costs of ‘Free’ Cloud AI Tiers
A free cloud AI tier does not cost zero. It costs something other than dollars: your data, your reliability, your…
InsightsAgentic AI explained: what it changed for local AI
Agentic AI explained without the hype. Stripped down it is one real shift: a model that answers questions became a…
InsightsLocal Deep Research vs Perplexity and the Cloud
Local deep research vs Perplexity: a research engine on your own machine keeps every query private and charges nothing per…
InsightsOpen WebUI vs Jan: The Local ChatGPT, Picked
Open WebUI vs Jan: two ways to put a private ChatGPT in front of someone. A feature-rich browser workspace, or…
AnalysisDo you need an agent framework? smolagents, and when to skip it
Do you need an agent framework at all? smolagents vs the alternatives, and why most of the noise is selling…
ResearchWhich Local LLM Should You Actually Run in 2026?
The best local LLM in 2026 is not the biggest one. It is the model that fits your RAM with…