BLOG
Knowledge Share
Technical articles, tutorials, and insights
Found 2 posts
AI AgentSubAgentMulti-Agent
SubAgent Architecture Deep Dive: How AI Systems Achieve Specialization Through Delegation
Starting from the engineering problem of context explosion, this article unpacks the core model behind SubAgents — isolated context windows, capability constraints, description-driven delegation, three execution modes, and two communication paradigms — with a complete look at Claude Code's implementation.
·12 min read
OpenClawNode HostCanvas
OpenClaw Deep Dive (6): Node Host, Canvas, and Sub-Agents
Starting from "how an AI assistant breaks out of a single-process boundary," we derive the design of the Node Host (remote execution sandbox), Canvas (mobile interactive UI), A2UI (native bridge), and Sub-Agents (parallel task decomposition).
·9 min read