Deep-Dive: Zhipu AI's GLM-5 and Local Open-Weight MoE Serving
Analyzing Zhipu AI's GLM-5 architecture: Mixture-of-Experts routing, controllable reasoning tokens, and local deployment using vLLM and SGLang.
Read Post →Featured Projects
View All Projects →Latest Blog Posts
Read All Posts →Connecting Google Antigravity and Gemini to OpenClaw: A Complete Migration Guide
Step-by-step developer tutorial on migrating your self-hosted OpenClaw desktop backend from Claude Code to Google Antigravity and Gemini CLI on macOS.
Read Post →Gemini 3.8 Live & Extended Thinking: Sub-200ms Audio-to-Audio and Background Reasoning
Under the hood of Google Gemini 3.8 Live: native speech-to-speech architectures, sub-200ms conversational latency, and asynchronous Extended Thinking with background tool execution.
Read Post →