AIHermesAgents
Hermes: an agent that remembers, routes and ships
Skills, persistent memory, model routing and MCP tooling — what an agent runtime needs before it's useful for real work.
· 2 min read
Field notes
The BEINNO blog.
Notes from BEINNO on building AI products — machine learning, LLM apps, and shipping them to production.
- EngineeringModel RoutingLLM
Model routers: one endpoint, many models
A router picks the right model per request — by task, cost, latency or availability. It's the single highest-leverage piece of AI infrastructure you can build.
· 2 min read
- AIOllamaLocal LLMs
Local models vs cloud models: how we choose
Privacy, cost per token, latency and capability all pull in different directions. Here's the decision rule we actually use.
· 2 min read