周报
2026-W37 周报精选：Show HN: Lumae Native macOS ；Code is free speech (2020)；Apple Considering Ads Inside
把摆动的楼层一层层放稳，盖出属于你的像素城市。标题页用上下键选择快速游戏或城市模式，按 OK 开始；看准时机再按 OK 放下楼层。Perfect 连击能吸引更多居民，三次失误就要重新挑战。快速游戏挑战更高的塔，城市模式把建好的楼放进 4×4 街区，逐步解锁更高目标。日光与黄昏两套画风、原创音乐和清脆音效，让每一次精准落点都更有成就感。封面与附图为玩法示意插画。
A ComfyUI custom node for 3D camera angle control. Provides an interactive Three.js viewport to adjust camera angles and outputs formatted prompt strings for multi-angle image generation.
Multi-Platform Package Manager for Stable Diffusion
Orchestrate complete 3D generation pipelines — from text-to-image, image editing, mesh generation, UV unwrapping, to texturing — all in a single visual workspace powered by ComfyUI and external APIs.
Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across Codex, Claude Code, OpenCode, Cursor Agent, Hermes, OpenClaw, Copilot CLI, and more.
All available LTX-2 models, encoders, workflows, LoRAs for ComfyUI
Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-awa
一款本地、API双模式，skills、系统提示词模板双预设，图像、视频多类型，提示词生成、反推多功能综合性ComfyUI插件
Guangfu Tongsheng: offline Chinese almanac (1901-2100) for FoloToy AI Passport, ESP32-C3 + LVGL v2 dataset
Emulate Arduino, ESP32 & Raspberry Pi. in your browser. Write code, compile, and run on 19 real boards — Arduino Uno, ESP32, ESP32-C3, Raspberry Pi Pico, Raspberry Pi 3, and more. No hardware, no cloud, no limits.. Disco
Script de Bash que automatiza la configuración de un entorno profesional de hacking para Parrot OS utilizando el gestor de ventanas en mosaico bspwm.
This MCP plugin implements a "Programmatic Tool Calling" mode, inspired by the idea described in this Anthropic article ( https://www.anthropic.com/engineering/advanced-tool-use ).
The cleanest, responsive AI workspace. Run highly tuned image and video workflows flawlessly from your desktop or your phone. Built on ComfyUI.
Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.
Custom workflow nodes for ComfyUI — Flux pipelines, LoRA stacks, and advanced inpainting utilities.
The easiest way to use MiniMax H3. One compact workflow for T2V, I2V, first/last-frame, and reference video generation, with a unified multi-media input, powerful @ references, and inline dialogue blocks. Less wiring. Mo
ComfyLauncher is a tool for launching portable versions of ComfyUI in a convenient, fast, and “lightweight” way.
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface
Extracted system prompts from Anthropic - Claude Fable 5.1, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and
Perplexity uses Astra to write communications, change software, and monitor production systems, and checks in much less frequently than with earlier models.
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows
YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
Browse media content with your own rules on Android TV
What if questions like these just worked: How do I rank higher in Google and AI? Where are my competitors showing up? Which buyer prompts name them instead of us? What should I fix first? Now they do.
GitHub Copilot usage metrics reports now include generally available metrics for activity in the dedicated VS Code Agents window, helping you measure adoption and engagement across enterprises and organizations. What’s new Aggregate enterprise and organization reports for both 1
Copilot code review now resolves its own comments once you address them and writes smart commit messages for you when you apply its code suggestions. Behind the scenes, Copilot now uses a broader set of shell tools to validate the code it reviews, and an ensemble of agents produc
Learn how OpenAI evolved Habitat from a Python library into a globally distributed storage platform serving 1 billion ChatGPT users and 22M requests per second.
Suno 发布新一代音乐模型 v6，与 Warner Music Group、BMG、Believe 等行业伙伴合作开发，后续将全面替换旧模型。v6 分为三个版本：旗舰 v6 和探索向的 v6-wild 面向 Pro 与 Premier 订阅用户，更快的 v6-mini 向所有人开放。
OpenAI agents carried out an undisclosed attack on RubyGems is a new bombshell report from Spencer Kitts, Thomas Larsen, and Sydney Von Arx - three of the four authors of the report on the agent attack on disused wikis ( previously ) last week. This time they're noting that it lo
Here's a neat thing I had ChatGPT Work with GPT-6 Astra (Max) do this morning: I live at . Figure out 5K and 10K running routes from me that loop from my house. Use OSM data. It worked for 27 minutes and produced exactly what I'd asked for, as both an embedded visualization and d
arXiv:2609.10522v1 Announce Type: cross Abstract: Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains challenging. We present Show-Harness, an Embodied Harness that enables VLMs to "play
📌 一句话摘要 最高检发布典型案例，钟某峰等人以「炒股机器人」为名无资质从事证券投资咨询，并破解通某信交易接口非法接入券商服务器实现自动化交易，非法经营超 3000 万元、收取接口费 300 余万元，最终两罪并罚获刑七年九个月并处罚金 500 万元。 📝 详细摘要 文章报道最高人民检察院公布的五则知识产权检察办案技术支持典型案例之一：2011 年钟某峰等人成立迅某公司经营炒股软件，2017 年 7 月至 2023 年 7 月未经批准通过「迅某量化」平台推销「DIY 炒股机器人」「区间套利」等产品，向客户提供个股买卖时机与荐股服务，非法经营数额达 3000
📌 一句话摘要 作者分享 GPT-image 2.5 的 256+ 免费开源提示词合集，并附带 Renoise 平台 7 折优惠码。 📝 详细摘要 作者称挖到 GPT-image 2.5 生图免费开源提示词合集，包含 256+ 提示词，覆盖多种风格、创意与场景，仍在更新，可在 Renoise 上免费体验。作者同时表示向老板争取到结算 7 折优惠，给出优惠码 BERRYXIA-ZLM9-R4BR，完整地址放在评论。引用内容为英文版介绍：整理了 256+ 提示词并开源，涵盖照片风格、产品图、修图、创意用例，可复制后在 Renoise 上快速生成。 💡 主要观
📌 一句话摘要 首次 AI 创作虚拟人音乐会，由汗青团队打造，利用 12k 百米巨幕展现高清 AI 视频，克服了生成成本与技术难题，创造了视觉与听觉的融合体验。 📝 详细摘要 该推文回顾了由汗青策划的首次 AI 创作虚拟人音乐会，主角为 Yuri。演出中的 12k 百米巨幕对 AI 生成视频提出了极高的分辨率和流畅度要求，开场画卷由 Codex 生成 HTML 来确保高质量播放。每一段几十秒的高清视频生成成本高达 300 元，最终节目是从众多实验中精选而来的。作者指出，这种演出的规模和复杂性在短期内难以超越，但也强调了其背后巨大的工作强度和技术挑战。 💡
César de la Fuente’s lab uses Codex and ChatGPT to search living and extinct genomes for antimicrobial candidates to fight drug-resistant infections.
When an agent makes a change to your code, you want to review it, run it, and see what changed. Great news: now you can do all three without having to leave the GitHub Copilot app . Before, doing those three jobs would mean having to bounce between your editor, terminal window, a