I collect field notes and experiments on agent runtimes, memory, orchestration, protocols, and AI infrastructure, with links to code where an idea has one.
research note
Agent runtime concepts
Execution loops, role boundaries, termination rules, persistent state, and runtime-level failure handling.
#runtime#agents#orchestration
agents architecture diagram. Nodes: ingress, router, planner, executor, state, audit. Flow: ingress to router (primary); router to executor (primary); executor to state (primary); router to planner (supporting); planner to state (supporting); executor to audit (feedback).
active experiment
Memory models for LLM systems
Comparing episodic, semantic, compressed, and affective memory for agents that need continuity.
#memory#retrieval#state
memory architecture diagram. Nodes: event, encode, episodic, semantic, recall, compress. Flow: event to encode (primary); encode to semantic (primary); semantic to recall (primary); encode to episodic (supporting); episodic to recall (supporting); recall to compress (feedback).
architecture note
MCP routing and tool boundaries
How tool catalogs, permissions, connector identity, and protocol adapters shape reliable agent execution.
#MCP#tools#protocols
tools architecture diagram. Nodes: agent, policy, MCP, adapter, tool, audit. Flow: agent to MCP (primary); MCP to adapter (primary); adapter to tool (primary); agent to policy (supporting); policy to adapter (supporting); tool to audit (feedback).
experiment
LLM inference on constrained hardware
Running local LLM chat and image generation on the Xbox Series S|X via UWP dev mode — ONNX Runtime GenAI plus DirectML, routed per workload under tight platform limits.