Post section

Your markdown here.

Reflections on Six Months of Hands-On AI Agent & AI Coding Experience
· โ˜• 15 min read
A 74-day retrospective on building EverLingo from scratch with OpenCode: how to organize docs and diagrams for effective collaboration with AI Agents; the evolution and pitfalls of the project's in-repo AI Agent harness (multi-agent collaboration); and how the product grew from a WeChat mini-bot into a multi-user containerized service.
EverLingo: An AI Language Companion That Remembers
· โ˜• 8 min read
EverLingo is an AI language companion that helps you learn in context and remember what you learn. It captures meaningful moments as you explore words, sentences, and ideas, turning them into useful notes. Later, EverLingo recalls those notes when relevant, making your learning more personal, connected, and effective.
Kanban - A Multi-Agent Collaboration Design Pattern
· โ˜• 4 min read
This article uses the example of generating a modern, technology-themed Mr. Bean TV episode script based on current global events to demonstrate the Kanban-based multi-agent collaboration design pattern. The article uses Hermes Agent, but the same approach can also be applied to other agent frameworks or even your own custom agents.
OpenClaw Egress Traffic Control โ€” A New Security Market for AI Agents
· โ˜• 9 min read
AI Agents shift security from static permission control to dynamic intent governance. Traditional sandboxing is insufficient against goal drift and prompt injection. This article demonstrates a system-level egress control PoC using cgroup, TProxy, and TLS SNI as a foundation for โ€œIntent Security,โ€ potentially defining the next security market cycle.
Intelligent Orchestrating the Home Lab and Smart Home by OpenClaw
· โ˜• 7 min read
This article demonstrates how OpenClaw Skills can orchestrate Home Lab and Smart Home intelligently. By encapsulating infrastructure knowledge, monitoring systems, ann automation APIs to structured Skills. An AI agent can troubleshooting servers, visualize operations physically, And deliver real time web information through smart home integrations.
The Concepts Anatomy of OpenClaw
· โ˜• 5 min read
OpenClaw is a self-hosted AI assistant. This article analyzes its design through documentation and LLM prompt tracing. It demonstrates prompt inspection with Home Assistant integration, showing how skills are discovered and loaded, and how agents securely handle sensitive information via environment variables instead of exposing them to the LLM.
Self-hosted Matrix Channel for OpenClaw - Take the red pill
· โ˜• 3 min read
This article explains how to self-host an OpenClaw AI assistant using a Matrix chat channel. It covers setting up a Matrix server, installing and troubleshooting the OpenClaw Matrix plugin, configuring access policies, and enabling secure, private AI interactions without relying on third-party messaging platforms.
AI-Based Job Position Watching from Company Career Pages(PoC) - Part 1
· โ˜• 5 min read
A proof-of-concept AI agent that automatically watchs company career pages for new job postings matching user-defined criteria. The agent navigates job portals, extracts relevant information, and stores it in a SQLite database for tracking and analysis.
A First Look at Proxying MCP Traffic with Agentgateway
· โ˜• 5 min read
As a key protocol in the AI Agent ecosystem, MCP support is one of Agentgatewayโ€™s core capabilities. This article records practical experience and observations from proxying MCP traffic with Agentgateway.
Agentgateway Implementation Analysis Part 3 - Http Proxy
· โ˜• 5 min read
This article attempts to analyze the implementation details of the Http Proxy main flow in Agentgateway. It allows readers to understand the working principle and implementation method of Agentgateway as an Http Proxy at the L7 layer.
Analyzing gemini-cliโ€™s Source Code with gemini-cli
· โ˜• 11 min read
Introduces how to use the `gemini-cli` command-line tool to analyze its own source code repository. Through a series of interactive commands, we will explore the design and implementation of `gemini-cli`. This method not only demonstrates the capabilities of AI tools but also provides developers with a new way to learn and explore.