Agent Substrate Environment
An Agent Substrate environment is the layer above the runtime that an agent loop actually wants: run this command, read this file, write that file, tell me …
Read more →building the agentic future in public
I run LLMs, robots, and gateways into production walls so you don't have to. Deep dives on the agentic mesh, agent runtimes, AI gateways, and the Kubernetes substrate that keeps autonomous systems honest — every post ships with a repo you can clone and receipts you can check.
How an agent proves who it is: SPIFFE, token exchange, and audience binding.
Open the hub →Controls that look like controls and are not, and what to put in their place.
Open the hub →The call path between agents and models: identity, spend, and policy in one place.
Open the hub →How agents find tools, which servers exist, and who those tools act for.
Open the hub →Start, stop, and isolate agents on Kubernetes. kagent and the substrate under it.
Open the hub →The house as a cluster, the cost of a capable machine, and who signs the test report.
Open the hub →Moving a Shrooly mushroom grower to open firmware and building a community app in public.
Open the hub →Honest verdicts on AI gadgets that duplicate your phone, paywall the basics or ship hype.
Open the hub →An Agent Substrate environment is the layer above the runtime that an agent loop actually wants: run this command, read this file, write that file, tell me …
Read more →A Kubernetes sandbox platform is what Agent Substrate still is after you ignore the word agent: a pool of sandboxes, native suspend and resume, rehydrate from …
Read more →Scheduling agent sandboxes is the job Agent Substrate does not do. It multiplexes many actors onto a small pool of warm workers, which is packing. When the …
Read more →Scheduling sandboxes for RL is a multiplexing problem: each training step fans out into sandboxes that spend most of their wall time waiting on a model. …
Read more →GPUs for agents on Kubernetes should sit outside Agent Substrate snapshots. GPU memory is not a file the runtime can checkpoint. If you give the actor a …
Read more →Suspend-safe networking is a design where an actor can be checkpointed and restored on another worker without dropping the TCP sessions it was using. I do not …
Read more →Agent action verification should be a binary check on the call path, not a second large-model prompt that says it is 90 percent sure. Evaluate a yes/no …
Read more →An agent platform at scale is not more pods. It is identity, scheduling, and suspend policy for fleets where most sessions are started by other agents. Replica …
Read more →kubectl is lying to you. Agent Substrate keeps the workload out of pods, so kubectl get pods shows a quiet WorkerPool while agents restore from snapshots, run …
Read more →Sandboxed networking for agents means the actor does not inherit the worker’s view of the network. Each actor needs its own isolation, default-deny …
Read more →