engineering 23
- Hermes, OpenClaw, NanoClaw, ZeroClaw, and IronClaw: Choosing the Right Agent Architecture
- I Audited the OpenVPN Server I Wrote a Guide For
- Codebase Memory for Coding Agents: Graft, Graphify, and codebase-memory-mcp
- When a Rails or LMS Platform Becomes Hard to Change
- When Ubuntu Builds Fail on libvips but macOS Does Not
- A Portable Workflow for Testing Small Local LLMs on Modest Hardware
- Orchestrating Hermes with Local Gemma: Cheap Routing, Delegation, and Safe Rails Workflows
- Agent 基建的三层爆发：电脑、运行时、技能方法论
- Tightening a dev VM that was quietly living without a firewall
- Golden Rules for Cheaper, Safer LLM Agents
- Loop Engineering, Graph Engineering, and the Nature of Working with LLMs
- When an Always Free server gets smaller
- The CI failures that moved every time you reran them
- Rebuilding a Small k3s Host Without Making It Precious
- Tightening Hermes Secrets with Bitwarden
- Don't Leave Good AI Workflows in Chat
- Building an AI English Conversation Practice App
- Running Hermes on a Cloud Machine as a Daily Routine Assistant
- LM Studio Local Agent Runbook: Pi and OpenCode Step by Step
- Tiny Puzzles for Testing and Debugging AI Agents
- How an LLM Coding Agent Actually Builds Software
- Using LM Studio and Gemma as a Local Engine for Coding Agents
- What Subagents Are Actually Good For in Codex