Miracle

Loop Engineering is the next step after prompt engineering. Most people still use Claude Code, Codex, Cursor, or Grok like a chat box: Prompt. Wait. Copy. Fix. Prompt again. This repo shows the next step: You stop prompting the agent. You design the loop that prompts the agent for you. Inside: → Daily triage loops → PR babysitter loops → CI sweeper loops → Dependency sweeper loops → Changelog drafter loops → Post-merge cleanup loops → Issue triage loops It also gives you CLIs to: • Scaffold a loop • Estimate token cost • Audit if your repo is ready • Add memory/state • Add human handoff • Add verification gates • Run agents safely through GitHub Actions The wild part is the shift in thinking. Prompt engineering was about writing better instructions. Loop engineering is about building a system where agents keep working, checking, fixing, and escalating without you babysitting every step. This is what AI coding looks like when it stops being a chat session and starts becoming an operating system for software teams. Repo: github.com/cobusgreyling/…

stop telling Claude Code/Codex "read this file". stop telling Claude Code/Codex "now read that one too". stop telling Claude Code/Codex "grep the whole repo". install codebase-memory. it indexes the Linux kernel, 28M lines, in 𝟯 𝗺𝗶𝗻𝘂𝘁𝗲𝘀. your repo takes seconds. index once and the whole repo becomes 𝗼𝗻𝗲 𝗴𝗿𝗮𝗽𝗵 of every function, file and dependency. one query replaces dozens of grep and read cycles. benchmarked across 31 real repos: → 10x fewer tokens on structural queries → 83% answer quality on complex tasks → 2.1x fewer tool calls two prompts. send them straight to your agent 👇

@CommandCodeAI Please fix your harness it gets stuck sometimes when I paste stuff in the chat box, and the model overthinks alot compared to opencode harness

We are doubling the usage limits to: 5-hour limit — 30% of your monthly credits Weekly limit — 60% of your monthly credits For all plans Go/Pro/Max. Provider and extra usage has no limit. We've also added major capacity, new providers, and a lot more GPUs to our self hosted infra. - Most models now run 5x to 8x faster - p50 TTFT: 5s → 965ms If Command Code felt slow the last few weeks, give it another go. It's fast now. Bigger plan dropping soon too. If you like the Go plan, this one's gonna hit home for y'all.

GLM 5.2 just beat Fable 5 at website design. 🌐 The crazy part: GLM is text-only. It can build the site, but it can’t inspect the result. So we paired it with Browser Use v2 multimodal QA subagents. > Reviews the site and finds bugs > Judges the aesthetics > Sends GLM targeted fixes to iterate on Build + full QA cost less than $0.75. Try it now ↓

Here's how I build beautiful UI using AI (My design workflow)

一个轻量的 Docker 镜像，把 Android 模拟器作为服务运行，适合 CI 测试和远程控制。 github.com/HQarroum/docke… 把 Android 模拟器和 ADB 服务打包进 Docker 镜像，跑在容器里，通过网络远程连上去操作。

New in-progress skill: /loop-me Interviews you about your work and finds opportunities for delegating your day-to-day work to AI

Introducing Hubble: the best notepad for you and your agents. - Feels like Notion or Apples Notes, but for Markdown - Live-reloading editor to collaborate with agents - Supports HTML-based apps to build interactive visualizations Free and open-source 👉 hubble.md

@codersaadi @hqmank @WindsurfCurrent @jeffwsurf Thank you, appreciated.

@miracle_vx2 @hqmank @WindsurfCurrent @jeffwsurf or whatever rules file you have. better use monorepo if it's a new project . use proper folderstructure segmentation , use obsidian if needed . i don't use a single model also opencode is good too , if extreme privacy isn't a concern u can use their free models when needed

Devin Pro users are reportedly getting unlimited GLM-5.2 access with 200K context. Not sure yet if this is a quantized model.

@codersaadi @hqmank @WindsurfCurrent @jeffwsurf Please do you mind sharing your workflow for getting a good UI out of this model ? I can't seem to get anything solid

@hqmank @WindsurfCurrent @jeffwsurf i do have a consistent structure . even sonnet/opus 4.6 was not following that and wasn't that much intuitive . with minor tweaks , 2-3 prompts (with a plan ) GLM 5.2 generated consistent results like m coding it myself .

@StudentOffersHQ @openmodel_ This model is an absolute work horse. As someone who can't afford these Ai sub, it's very helpful

DeepSeek V4 Flash is free right now. 1M context window. No card. 10 req/min. 100K tokens/min. Good enough to ship. @openmodel_ - swap base_url on Anthropic SDK.

@port_dev It is literally not usable, slow and cut off mid task, you start a new chat something

I’ve been testing GLM 5.2 and it’s genuinely impressive for coding. great news: you can try it for free in zcode -> free usage -> no API key needed -> no paid coding plan required link in second tweet👇

Yo I thought these guys were playing 😂

BREAKING: GLM-5.2 is now 1st on Design Arena. With an Elo of 1360, GLM-5.2 has jumped ahead of the now unavailable Claude Fable 5. And it's open weights. This is an improvement of 4 positions and 27 Elo points to achieve one of the highest Elo scores in our code categories since Design Arena started. Huge congratulations to the @Zai_org on the release!

@Zai_org @CommandCodeAI when ?

Introducing GLM-5.2: Frontier Intelligence, Open Weights - Significant improvements in coding and agentic tasks - Strong long-horizon capabilities with a 1M context window - Two levels of reasoning effort: GLM-5.2 (max) pushes the limits, while GLM-5.2 (high) strikes a strong balance between performance and token efficiency - MIT-licensed open weights - Same API pricing as GLM-5.1 Tech Blog: z.ai/blog/glm-5.2 Weights: huggingface.co/zai-org/GLM-5.2 API: docs.z.ai/guides/llm/glm… Coding Plan: z.ai/subscribe Chat: chat.z.ai

🌘 Meet Kimi K2.7 Code HighSpeed! A high-speed mode of our latest open-source multimodal coding model, Kimi K2.7 Code. ⚡️ Up to 6× faster: Around 180 tok/s on coding tasks with median-length inputs, and up to 260 tok/s on shorter-context tasks. 🔷 Rolling out to Kimi Code Beta Program members, Kimi API developers, and Kimi Business users. (Access will remain limited for now due to capacity constraints.) 🔷 No invite needed. Anyone who joins the Beta Program has a chance to get access 👉 kimi.com/code/beta Open intelligence should be instant, affordable, and borderless. We'll continue improving the model and expanding access as more capacity becomes available! 🔗 Kimi Code: kimi.com/code 🔗 API: platform.kimi.ai

@UiSavior Claude

Step-by-step guide: Claude Skills for Designers. 👀

Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇

@pigeon__s @Zai_org They literally said the weight will be dropped next week, learn to read, oh my God.

@Zai_org > Intelligence should be open > checks huggingface > nothing ever happens

Intelligence should be open, accessible, and ready to build with, empowering every developer, everywhere. GLM-5.2 is now available to all GLM Coding Plan users, including Lite, Pro, Max, and Team plans. docs.z.ai/devpack/latest… As our new flagship model, GLM-5.2 delivers powerful coding capabilities, usable 1M-context support, and continued strengths in long-horizon tasks. API and Chatbot services will launch next week. The model will also be officially open-sourced next week under the MIT License. The future of AI is open, and it belongs to the people.