research note
Agent runtime concepts
Execution loops, role boundaries, termination rules, persistent state, and runtime-level failure handling.
#runtime#agents#orchestration
agents architecture diagram
Research
Notes and experiments on agent runtimes, memory, orchestration, protocols, and AI infrastructure.
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
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
experiment
LLM inference on constrained hardware
Porting llama.cpp to the Xbox Series S|X via UWP dev mode — a study in running local inference under tight memory and platform limits.
#llama.cpp#on-device#C++
xllamaworkflow architecture diagram