Harness Development Kit: Ship local AI apps in TypeScript
One command scaffolds a working TypeScript application with the model, the agents, the retrieval and the runtime already inside it — and your code runs inside generation rather than around it.
Dispatch · August 2026 02How Lloyal turns the model's working memory into agents on the GPU
A walk down the stack, from TypeScript scope to the attention mask — how fork becomes an owner bit per cell, a cohort of agents becomes one batched decode, and the pressure counter becomes an admission controller your code reads.
Dispatch · August 2026 03You already know this architecture. It shipped in 2007.
Familiar plumbing, novel use-case. Lloyal's serving stack maps noun for noun onto the stack that carried Rails for two decades — Rack→binding, Puma→host, Unicorn→relay, config.ru→driver.
Dispatch · July 2026 04Shifting the harness left: 10 concurrent GLM-5.2 agents for the compute of one
How we served a deep-research app with 10 GLM-5.2 agents on one deployment — one shared KV context, one llama_decode per step, paid in memory not compute. Full trace, config, and cost receipt published.
Dispatch · July 2026