Local AI Lab For Developers

Build a local AI lab: run Ollama like a service, measure tokens and speed, and create developer tools that grow into safe, repo-aware agents.

3 articles in series

A developer laptop terminal streaming local model output with latency metrics overlayed.

AI on Your Computer: Run a Local LLM Like a Service

January 20, 2026·byJoshua Morris

Run a local LLM on macOS, Linux, or Windows, call it over HTTP like a real service, stream output in Node/Python/Go/C++, and measure TTFT + throughput to understand what's actually happening.

AILocal DevelopmentSoftware Engineering

A developer laptop showing token boundaries highlighted across text, with token counts and latency estimates in the margin.

Tokens Are the Unit of Pain: Tokenization You Can See

January 27, 2026·byJoshua Morris

Tokens are the meter your model charges in: context, latency, and cost. We'll make tokenization visible using your existing local Ollama service—first via a CLI token inspector + heatmap, then with a live-updating browser playground.

AILocal DevelopmentSoftware Engineering

A clean Solarized Light diagram showing a ceiling line above stacked token blocks and a budget meter.

Context Is a Budget: Truncation, Chunking, and Staying Under the Limit

July 13, 2026·byJoshua Morris

Context limits aren’t vibes—they’re math. Learn truncation behavior, token budgets, and RAG chunking so your model stops forgetting the important part.

AILocal DevelopmentSoftware Engineering

Back to All Series