Claude Code on Lynx Tech Blog

Obsidian + Claude Code: My Founder OS Dual-Driving Workflow

Sun, 13 Sep 2026 17:45:00 +0800

The previous post, I Built Myself a Founder OS With Claude Code, covered how to build a knowledge base. This one covers how to use it. Specifically: how to let human and AI collaborate inside the same knowledge base. I read the dashboard and tweak notes in Obsidian; Claude Code runs batch triage, fills templates, and migrates files in the terminal. Both sides edit the same Markdown files, and Git records everything.

I Built Myself a Founder OS With Claude Code: Reclaiming 155 Scattered Files

Sun, 13 Sep 2026 17:30:00 +0800

How It Started: What 155 Files Taught Me Start with a number: my WSL home directory contained 155 Markdown files. Not 155 notes — 155 “important but I don’t know where to put them” files. Among them: 41 industry research reports (ERP selection, VPS migration, LLM rankings), 30 ops postmortems (written at 3 AM when services died), 20 personal documents (my cousin’s college application plans, my own resume), and hand-written handoff sheets for a dozen projects.

The Complete Technical Routes for Hermes to Control Claude Code: From Terminal Invocation to Agent Interoperability Protocols

Sun, 13 Sep 2026 16:15:00 +0800

One-Sentence Summary Hermes (a Telegram bot gateway) controlling Claude Code (Anthropic’s CLI coding agent) has 7 technical routes: direct terminal invocation, SDK programmatic API, MCP bidirectional communication, A2A Agent-to-Agent protocol, ACP Agent Communication protocol, Hooks system, and Cloud sessions. Hermes already has codex_app_server and copilot_acp subprocess runtime templates — adding a Claude Code runtime is essentially copying an existing pattern. For Telegram bot scenarios

Is My Claude Code Memory System the Most Mature? — DIY Cross-Harness Setup vs. the Open-Source Ecosystem

Thu, 10 Sep 2026 00:00:00 +0800

The verdict up front No — it is not “the most mature on the internet,” because there is no absolute most-mature; it depends on which problem you are solving. But placed against the 2026 open-source ecosystem, my system sits firmly in the top tier of self-built setups, with one strength almost no open-source project has: a single-source-of-truth architecture spanning 6 harnesses. I also have to be honest: the industry is productizing this exact capability. The highest-starred project,

What the Server Knows, the Browser Shouldn't Get: Mapping the Frontend Secret-Leakage Surface

Wed, 02 Sep 2026 01:00:00 +0800

Let’s start with a scenario. You’re building a SaaS product: the backend is connected to a cloud database, the frontend is Next.js, and iteration is moving fast. Before launch, you ask the security team to run a black-box test. On the third day, the report comes back with two high-severity findings: C1: On the homepage, “View Source” reveals that the JSON inside __NEXT_DATA__ contains the full backend configuration that should have existed only on the server side—database address, message queue

Full Health Check of CPA Model Pool: Which of 80 Models Are Alive, Smart, or Running Naked

Sun, 23 Aug 2026 00:00:00 +0800

Last month I wrote an article testing six Claude Code models. This time I’m broadening the scope: my local CPA (local model gateway) has 80 models connected, and I did two things — first, sent real requests to each one to check liveness, then gave the survivors a puzzle-resistant intelligence test, and finally cross-validated against public leaderboards. Bottom line up front: listing a model ≠ it works. Of the 80 models, 59 are text models, and only about 30 could actually hold a conversat

Solo Multi-Channel Content: How I Built My AI Automation Pipeline LynxPipe

Thu, 20 Aug 2026 00:00:00 +0800

Running a blog, a Telegram channel, and a WeChat public account all by myself—the real bottleneck isn’t running out of ideas, it’s keeping up. Every day there’s an overwhelming flood of valuable AI news, and manually translating, rewriting, sourcing images, laying out, and distributing it all can eat up half a day before you even start. So I architected it as a pipeline I call LynxPipe: raw inputs go in, polished articles come out, and distribution to the blog, TG, and WeChat h

A Comparative Review of Eight IDEs in the AI Era: Memory Usage, Runtime Efficiency, and Bug Signals (Multi-Source Verification, August 2026)

Wed, 19 Aug 2026 00:00:00 +0800

Stop taking that optimistic little “lightweight 400MB” number on IDE landing pages at face value—the 2026 generation of AI IDEs has entered the era of “memory inflation.” In a Copilot Chat session stretched across 18 hours, the VS Code extension host can balloon from 500MB to 80GB+, while Zed has even recorded an extreme 185GB case on macOS. This article offers an in-depth comparison of eight mainstream AI IDEs. Using multi-source online verification plus adversarial review, we cross-check the a

ccswitch Edited the Model, Claude Code Didn't Budge: A Three-Layer Override Root-Cause Diagnosis

Tue, 18 Aug 2026 21:36:00 +0800

Origin: Three Edits, Zero Effect I opened ccswitch (v3.19.2, the Windows-side Claude Code config switcher), clicked “edit provider,” changed the Opus-tier model, and saved. Restarted Claude Code — still running the old model. Edited, saved, restarted again — still no change. “Doesn’t change” problems are the worst kind to guess at. Below is the process of forcing out the root cause with logs and a field-by-field database comparison. The conclusion is more tangled th

From Manual Post Review to Semi-Automated Improvement: My Telegram Channel Quality Loop, and the Next Step Toward Full Automation

Sat, 15 Aug 2026 00:00:00 +0800

From Manual Review to AI-Driven Loop: How I Automated My Telegram Channel Moderation I run a Telegram channel @Lx_groups focused on free AI resources—free API quotas, limited-time offers, open-source projects, and industry news. The pitch is simple: “genuinely free,” no gray-market stuff, no ads. Behind the scenes, a Cloudflare Worker pulls from upstream TG channel preview pages, GitHub Atom feeds, and major tech company RSS feeds, deduplicates via KV storage, and pushes curated cont

Hands-on Test of Six Claude Code Models: Who’s Fast, Who’s Smart, and Who’s a Lottery

Sat, 15 Aug 2026 00:00:00 +0800

Claude Code’s model picker currently has six options sitting in it: qwen3.8-max, glm-5.2-fast-preview, glm-5.2, deepseek-v4-pro-0813, qwen3-coder-next, and grok-4.6. All of them are routed through my local CPA, a local model gateway, to their respective upstream providers. In day-to-day use, my impressions were vague: “this one feels faster,” “that one feels smarter.” Gut feel is unreliable, so I spent an evening putting them on the same starting line and benchmarked speed, thinking time, long-i