ZhuoQi Devzhuoqidev.comRSSllms.txt
drag the cards

Shipping agents into real products

field notes, written in Chinese and English

Liu ZhuoQi · AI Application Engineer · Agent Systems
Pencil sketch portrait of Liu ZhuoQi
me, most days ~
Outcomes is only as good as the rubric you write.
— from Agents That Check Their Own Work and Tidy Their Own Memory
series/

Agent Architecture Deep Dives 6 posts

  1. 01Claude's Tool Calling Paradigm Shift
  2. 02Five Codex Harness Designs Worth Copying
  3. 03Why Codex Does Not Give the Model Every Tool
  4. 04Agents That Check Their Own Work and Tidy Their Own Memory
  5. 05Agent plugins, explained
  6. 06Inside an agent plugin
series/

Local AI Hardware, Tested 3 posts

  1. 01Is a Mac actually good for local LLMs
  2. 02Half-rate tensor cores, explained
  3. 03The half-speed tensor core
CKACKSRHCE
zhuoqi@dev — zsh
$ whoami
Liu ZhuoQi · AI application engineer (agents)

$ ls posts/ | wc -l
22  # every post also in Chinese

$ cat focus.md
agent memory · grading & review · inference
Temporal workflows · shipping to prod

$ open latest.md

Projects

AI vendor statusWhat the official status pages of OpenAI, Claude, Gemini, xAI, Mistral, Amazon Bedrock, DeepSeek, Kimi, MiniMax and others say right now, set as a newspaper front page — the worst one makes the headline, every vendor gets a weather, open one for components and incidents in progress; vendors without a status page are listed too, with the reason. A Cloudflare Pages Function reads each vendor at most once a minute and never calls a model.llm-relay-auditAn open-source Agent skill that compares an AI API relay (new-api / one-api / sub2api) with the official API item by item: real model or swapped, injected prompts, official original video, swallowed parameters, real charges. Every raw request is logged, and it ends with an external evidence PDF and an internal decision card. Python + the Agent Skills spec, one-line npx install.ArgusAn open-source, frontend-only agent harness for long-video understanding: the video file never leaves the browser, multi-provider LLMs via Vercel AI SDK, with frame-extraction / memory / sub-agent tools and dual-CDN publishing. Vite + React + TypeScript.VaneA self-built AI Agent system that ran in production from 2026-07 to 09 and is now paused: multi-source ingestion → LLM personalized scoring → Feishu push, with a user-profile feedback loop. Go + Temporal + A2A protocol + React, full-stack.
LatestAgent Architecture Deep Dives #05

What Is an Agent Plugin, Really? The Parts Inside and Three Generations, in Pictures

Claude Code, Codex and Cowork all have "plugins" now, but this generation has little in common with the ChatGPT plugins of 2023. This is the illustrated beginner edition. No config files and no protocols; four pictures show what a plugin is, where it steps in after you say one sentence, which three generations led here, and three things to know before you install one.

Read →
Deep dive · 07-30

How Agents Remember You

From Ebbinghaus to engrams, then a code audit of Mem0, Letta, Graphiti and three more.

Say hi on WeChat

Liu ZhuoQi's WeChat QR code

Scan it in WeChat, or long-press it on your phone

Mention why you're reaching out, or I might miss it.