Research

Notes and experiments on agent runtimes, memory, orchestration, protocols, and AI infrastructure.

research note

Agent runtime concepts

Execution loops, role boundaries, termination rules, state persistence, and runtime-level failure handling.

#runtime#agents#orchestration

active experiment

Memory models for LLM systems

Comparing episodic, semantic, compressed, and affective memory as infrastructure for stateful agents.

#memory#retrieval#state

architecture note

MCP routing and tool boundaries

How tool catalogs, permissions, connector identity, and protocol adapters shape reliable agent execution.

#MCP#tools#protocols