Explainer
Open weights, open code, open enough for what?
Inspect the actual artifacts and permissions behind an openness claim instead of treating open as a single product feature.
Open models & licensesData & training
Source-based4 min ↗
A CONNECTED RESEARCH AREA
Compute & open ecosystems
Understand the infrastructure underneath an AI product: inference, local deployment, training data, licensing and portability.
Compute & inferenceLocal & edge AIOpen models & licensesData & trainingCost & portability
Start exploring.
Source-based reading in this area.
Guide
Your local AI assistant may still use the internet
Draw the model, retrieval, tool and logging boundaries before assuming that a local application is fully offline.
Local & edge AIData flow
Source-based4 min ↗
Explainer
Why KV caching turns context into a capacity question
Understand the memory side of token generation, then ask better questions about prompt length, concurrency and serving limits.
KV cacheServing capacity
Source-based4 min ↗
Repository
Read Local Deep Researcher before running it
A repository walkthrough for mapping model, search and report stages into an explicit configuration and data-flow record.
Local modelsConfiguration
Source-based4 min ↗
Checklist
Test API portability with a behavior contract
A reusable worksheet for comparing the responses your application depends on when two servers expose similarly named endpoints.
API portabilityMigration
Source-based4 min ↗