DevTrendsDeveloper trends
Accent color

DEV TRENDS / DAILY DISCOVERIES

Oct 31, 2026 · What developers are building

Daily discoveries from developer communities, independent makers, and open source.

Today’s cardsBrowse today’s discoveries one at a timeRead 0 / 88

Claude 余光

在浩瀚的星河中，记录你被停用的 cladue 账号 ｜ In the vast expanse of the starry sky, record your deactivated cladue account

Original
LanguageJavaScriptDTWeb appDTWebOriginalclaude
VibeCafé
0

KanaCraft 卡娜日语 / 卡娜英语

面向中文用户的日语与英语自学网站，日语从零基础五十音与听写入门，覆盖 JLPT N5–N1 词汇和教材词书，英语用打字、听写、卡片与连连看背单词并带语法知识库，覆盖四六级、考研与雅思托福词库；基础功能免费、会员可选 — 浏览器即可用，适配手机、平板与电脑 - 卡娜英语

Original
DTWeb appDTWeb
Chinese Indie Developers
—

豆门

面向拼豆爱好者的图纸识别与制作 App，导入现成图纸或照片后核对网格与颜色，编辑导出并记录制作进度；免费、无需注册，支持 iOS / iPadOS 与 Android - 原创图纸与入门教程

Original
DTResearch & learningDTContent / resourceDTiOS
Chinese Indie Developers
—

ChanScout

中文 Telegram 公开资源目录，收录可核验的频道、群组与机器人，支持分类浏览与持续核验，免费使用

Original
Chinese Indie Developers
—

BGX

A free, privacy-first background removal tool powered by AI.

LanguageTypeScriptDTWindowsOriginalbackground-removalOriginalbgremover
Chinese Indie Developers
5

Iris Analytics

A lightweight, open-source website analytics dashboard powered by Cloudflare Pages + Analytics Engine

LanguageLessDTData & operationsDTWeb appOriginalanalytics
Indie Dev · Programmers
19

Motionboard

发布片镜头配方库，38 个 Apple、Linear 等官方发布片镜头的 HyperFrames 复刻，附 agent skill，npx skills add 一行安装让 Claude Code 做发布片

Original
DTAgent extensionDTSkill / pluginOriginal程序员版
Indie Dev · Programmers
—

Yenpo：和 AI 一起写项目时，读懂它改了哪些代码（macOS）

Yenpo 是一个 macOS 桌面应用，用来在和 Claude Code、Codex 这类 agent 一起写项目时，读懂和审查 AI 写的代码，跟上它的思路。它不接入 Claude Code、Codex、Cursor 或 GitHub，看的是你本地仓库里的改动。 直接读取本地的 git ，按改动列出 AI 改过的文件，逐个看行内 diff 内置 AI Reader，默认只读，可以对着代码问"这段为什么这么改"；用你自己的模型服务商 自带终端和编辑器，看完可以顺手改 不需要注册账号，应用内没有遥测 支持 macOS 14+，界面有 10 种

Original
DTDesktop productivityDTSoftware developmentDTAgent extension
Weekly Submissions
—

HACKERS：帮新手挑一个真能做完的黑客松或 Kaggle 比赛

把 Devpost 上正在报名的黑客松和 Kaggle 比赛放在一张图里，按“新手能不能做完”排序。 每个比赛都标出奖金、倒计时和新手友好分，友好分的计算公式公开在页面上。图上横轴是剩余时间，纵轴是友好分，一眼能看出哪些还来得及。 截止日历把未来几周的截止日期排在一起，方便规划周末项目。 附新手攻略，覆盖选题、组队到提交，中英文都有。 免费，不用登录。英文版：

Original
DTWeb appDTWeb
Weekly Submissions
—

记问：会自己对账的安卓记账本，导入微信 / 支付宝账单不重复

记问 是我自己做的安卓记账 App，免费，源码公开。 平时手记，月底把微信、支付宝账单整段导进来，自动和手记配对、不重复记；退款自动挂回原单，转账、提现、信用卡还款单独算。拿不准的几百笔分类可以打码后复制给自己用的 AI 按组整理，再粘回来一次改完。 数据只存在手机里，App 不联网，也不调用任何 AI 接口。每次导入前自动备份，导错能整批撤销，导入后手动改过的不会被撤掉。 没有真实账单也能试：仓库 docs/samples/ 里有一个月的虚构微信、支付宝账单。 下载：

Original
LanguageJavaScriptDTSoftware development
Weekly Submissions
2

Bases Helper：Obsidian Bases 阅读追踪、公式排错与筛选实践指南

自荐一个英文的 Obsidian Bases 实用教程集，面向已经开始用 Bases、但卡在属性类型和公式细节的用户。 入口： 目前有四篇免费指南，配有可复制表达式、实际界面截图和可下载的练习库： 阅读进度追踪：每本书一个笔记，用已读页数和总页数生成进度条。 公式排错：检查字段名、数字与文本类型、0 与缺失值，以及公式列和数字排序。 按年月分组：用包含年份的月份键，避免不同年份的同一个月混在一起，并处理缺失日期。 组合筛选：文件夹、状态、标签，以及全局筛选和单个视图筛选的关系。 希望提供的价值是让读者能在独立练习库里复现问题，再应用到自己的笔记，而不只是复制一段不知道该放在哪里的公式。 网页和练习文件无需注册、无需付费；需要启用 Obsidian 内置 Bases，不依赖社区插件。阅读进度来自手动维护的数字属性，不会自动统计正文勾选框，也不与阅读器同步。 测试范围是 macOS 上的 Obsidian 1.14.5；其他版本和移动端未验证。测试方法及限制。 关系与制作说明：这是 Bases Helper 项目方自荐，与 Obsidian 官方无关。文章及本投稿使用了 AI 辅助，文章实例已在原生 Obsidian 中检查，站点所有者审核后发布。此次投稿由 AI 助手在站点所有者明确授权下提交。

Original
DTResearch & learningDTSoftware developmentDTWeb app
Weekly Submissions
—

TeapotRouter：给 Claude Code / Codex 的按量计费 API 网关

自荐（利益相关：作者本人） TeapotRouter 是一个面向 AI 编程助手的 API 网关：一个 Key 同时兼容 Anthropic 和 OpenAI 双协议，Claude Code、Codex CLI 改两个环境变量就能接入，按 token 计费。 为什么做这个 中转站市场口碑差，不是"中转"本身的问题，而是三件事：价格不透明、余额会过期、跑路没对账。所以这个站把三个承诺做成硬规则： 价格表全站公开：每个模型的基准价与实付口径写在明处，另有机器可读的 JSON 价格接口，方便比价工具直接抓； 余额永不过期； 计费日志可导出对账：每笔请求的成本、延迟、渠道都可查——Claude Code 烧 token 到底烧在哪，看得见。 其余：支付宝可充值（最低 $1）、多上游自动故障转移、支持退款（按剩余余额退，工单办理）。 彩蛋 名字和 logo 来自 HTTP 状态码 418 "I'm a teapot"——logo 就是「418 压扁成一把茶壶」，官网还专门做了一页 418 状态码小史（从世界上第一个咖啡壶摄像头讲到 RFC 2324）。 接入（Claude Code 示例） bash export ANTHROPICBASEURL= export ANTHROPICAUTHTOKEN=sk-your-key 上线两周的新站，欢迎批评。

Original
DTSoftware developmentDTAgent extensionDTAgent observability
Weekly Submissions
—

回响 QQ 助手：Windows 本机群聊工作台

回响 QQ 助手（QQ Reprise）：在 Windows 本机运行的 QQ 撤回重发、AI 群聊和独立官方群打卡工具。基于 NapCat / OneBot 11，名单、时间及策略分别配置。MIT 开源。

Original
LanguageJavaScriptDTResearch & learningDTSoftware developmentOriginalai-assistant
HelloGitHub Submissions
1

PageSift

Rust web scraper & crawler for AI agents: URLs, PDFs and Office files → clean Markdown/JSON. Firecrawl- and Jina Reader-compatible API, MCP server, Python/Node SDKs. Self-hosted single binary.

LanguageRustDTSoftware developmentDTAgent extensionOriginalai-agents
HelloGitHub Submissions
179

obra / superpowers

An agentic skills framework & software development methodology that works.

LanguageShellDTSoftware developmentDTAgent extensionOriginalai
GitHub Trending
309.9K

Orkas-AI / Orkas

Orkas is an open-source (MIT), local-first AI team for your desktop: a Commander turns your goal into to-dos and coordinates 16 built-in specialist agents plus Claude Code, Codex, OpenCode, OpenClaw and Hermes, with projects, scheduled automations and connectors. Free app for macOS & Windows; built-in models or your own keys.

LanguageJavaScriptDTAgent orchestrationDTContent / resourceOriginalagent-collaboration
GitHub Trending
6K

THU-MAIC / OpenMAIC

Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click

LanguageTypeScriptDTResearch & learningDTAgent orchestration
GitHub Trending
42.1K

bregman-arie / devops-exercises

Linux, Jenkins, AWS, SRE, Prometheus, Docker, Python, Ansible, Git, Kubernetes, Terraform, OpenStack, SQL, NoSQL, Azure, GCP, DNS, Elastic, Network, Virtualization. DevOps Interview Questions

LanguagePythonDTData & operationsDTSoftware developmentOriginalansible
GitHub Trending
85.8K

XIU2 / CloudflareSpeedTest

🌩「自选优选 IP」测试 Cloudflare CDN 延迟和速度，获取最快 IP ！当然也支持其他 CDN / 多个解析 IP 的网站 ~

Original
LanguageGoDTSoftware developmentDTWeb appOriginalcdn
GitHub Trending China
29.7K

OI-wiki / OI-wiki

star2: Wiki of OI / ICPC for everyone. （某大型游戏线上攻略，内含炫酷算术魔法）

Original
LanguageTypeScriptDTLifestyle & entertainmentDTSoftware developmentOriginalacm-icpc
GitHub Trending China
27.1K

vastsa / FileCodeBox

文件快递柜-匿名口令分享文本，文件，像拿快递一样取文件（FileCodeBox - File Express Cabinet - Anonymous Passcode Sharing Text, Files, Like Taking Express Delivery for Files）

Original
LanguagePythonDTAgent extensionDTMCP serviceOriginalanonymous
GitHub Trending China
8.7K

Infrasys-AI / AISystem

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

Original
LanguageJupyter NotebookDTLibrary / SDKDTContent / resourceOriginalai
GitHub Trending China
18.1K

langbot-app / LangBot

Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Kimi, openclaw / hermes agent, deerflow

Original
LanguagePythonDTSoftware developmentDTAgent extensionOriginalagent
GitHub Trending China
18.6K

gdy666 / lucky

软硬路由公网神器,ipv6/ipv4 端口转发,反向代理,DDNS,WOL,ipv4 stun内网穿透,cron,acme,rclone,ftp,webdav,filebrowser

Original
LanguageGo
GitHub Trending China
8.3K

SKI

Voice-first coding harness

DTSoftware developmentDTmacOSDTClaude Code
Product Hunt
197

WinnerAdSpy

Turn competitor ad insights into winning app campaigns

DTResearch & learningDTLifestyle & entertainmentDTAgent extension
Product Hunt
113

AC Bridge

Your smart lights show when Claude Code or Codex needs you.

DTAgent observabilityDTClaude CodeDTCodex
Product Hunt
70

Hemmed

Hide Mac menu bar clutter and pin individual actions

DTDesktop productivityDTDesktop appDTmacOS
Product Hunt
80

Specsight

Product observability for teams shipping fast with AI

DTBusiness & growth
Product Hunt
178

CubbyPad

Launchpad is back on macOS 26, and it's smarter

DTDesktop productivityDTmacOS
Product Hunt
59

ChainPoints

Flight Prices in Your Points, on Google Flights

DTResearch & learningDTSkill / pluginDTContent / resource
Product Hunt
69

Backenly

The autonomous backend for AI coding agents

DTSoftware developmentDTAgent extensionDTMCP service
Product Hunt
111

Agnos

Clean documents for AI, and see what was removed

DTWebDTWindows
Product Hunt
69

Mo

A little character on your Mac who does 232 tasks for you

DTmacOS
Product Hunt
67

SpaceO

Give AI agents their own screen on your Mac

DTSecurity & testingDTAgent extensionDTAgent observability
Product Hunt
62

Automatic deduction of FlashAttention kernel from ~25 lines of SQL

In this demo, we automatically deduce a FlashAttention kernel with ~25 lines of SQL, which just expresses vanilla attention. This is possible due to three portable SQL extensions that we’re building: - xarray-sql: a library that efficiently represents petabyte scale array datasets in the cloud as tables (relations). - ddx: a database extension that adds automatic differentiation in the style of JAX to standard SQL, assuming the above array data model. - einfold: a modular query planner for fast tensor contractions in vanilla SQL, again, assuming the above array data model. My hope is that the relational model and algebra provide fresh perspectives on how we might do accelerator programming. Here, our thesis is that separating the logical layers in a tensor program from the physical layers is both more correct and more scalable. If the Bitter Lesson is a central dogma of machine learning, then why not formalize it with relational algebra? If this interests you and you’d like to tinker with us at the intersection of database theory and ML systems, join us on Discord at https://xql.systems (link at the bottom). Cheers.

DTResearch & learningDTData & operationsDTSkill / plugin
Show HN
—

Fishoid: an ambient fish tank for your screen

I have built a cosy fish tank simulation you can leave on a large screen and watch from time to time. I like pixel art but didn’t want to be religious about it, so I think of it as pixel art adjacent. This summer, down with the flu, I started a small experiment. It ended up taking about 50-70 hours of my time, iterating over several months. There is a 24-inch display in my kitchen powered by a used Lenovo mini PC (previously it was a RPi, but I had to upgrade to get a better GPU). I used it to show a rotation of my home photos, but now I’ve switched it to show this fish tank. No prior game dev experience, but years of backend development and all the time spent reading indie dev blogs (honourable mentions Factorio and Banished) helped. I used LLMs to give me a hand. It rather felt like playing a game, maybe like Factorio a bit, switching from system design to art direction and back and learning more about game dev to make it look better and better. For me it became a way to express creativity I might otherwise not have had time for. Along the way I learned what marine snow is and how fish swim. One funny story was me curiously asking an LLM if it could find some research papers on fish swimming patterns and styles and base the implementation on that, and it did. I also used it to create a surprise for my wife’s birthday: on the day, three fish with QR codes appeared, each leading to a quest in the real world. But that is another story. Halloween is around the corner, so try the Halloween theme.

DTResearch & learningDTLifestyle & entertainment
Show HN
—

Rust based window switcher for macOS

3 types of switching themes (notch, liquid glass, carousel) - Shortcuts for window splitting and maximizing - Most resource efficient window switcher for macOS

DTDesktop productivityDTmacOS
Show HN
—

Similarity, a spiritual successor to 2000s-era OkCupid

This is a side project I've been working on on-and-off (mostly off) since the 1990s. I guess you would call it an experimental "dating site" though it's designed to be fun/interesting to people who aren't single (like me). You don't need to sign in to see how it works, so try it out. There is no swiping. The original inspiration was a 90s-era website called moviecritic.com that let you rate movies and get movie suggestions via collaborative filtering. I thought "hey, what about just matching me to the _people_ with the same taste instead?" And why just movies? The closest thing to this was 2000s-era OkCupid, before it was Tinderized. I want to capture its appeal, while making something novel. Similarity is not vibe coded, though I lean pretty heavily on codex (mostly the $20/mo plan - not a lot of tokens burnt here). The stack is java, guice/gwizard, elastic beanstalk, postgres (neon), react, jotai, and few cloudflare doodads. The match engine is a custom in-memory structure; getting the LLM to load test and optimize it was really a wow moment. Everything is PaaS and designed to scale by itself, cheaply, hands-off. I'm working on some ideas to help with the chicken/egg problem but for now I have low expectations. It's cheap to run and I have a day job. Would love feedback!

DTAgent extensionDTWeb appDTWeb
Show HN
—

I'm killing AI slop spam with a simple Google script

As a founder, I&#x27;ve been getting an increasing amount of useless unsolicited outreach, all of which is clearly generated using AI. For some reason, Google&#x27;s spam filter doesn&#x27;t flag these emails as spam, so my phone buzzes throughout the day (especially in the morning) when one of these AI-generated messages arrives. I know there are some subscription tools I could use to filter these out, and there are some friction-creating tools I can use to keep them out of my inbox (like the ones that force senders to prove they&#x27;re human 1x before their emails are delivered). But I figured there had to be a better solution that is (1) free and (2) not a hassle to people I correspond with. After a chat with Gemini, I ended up creating a Google script that works very well for my purposes. It simply takes any email that&#x27;s in my Inbox and if it&#x27;s from a sender that I&#x27;ve never emailed before, it moves it to a purgatory folder that I can review later. The script runs once a minute. Pros: this is simple and deterministic. Gemini tried to get me to build a script that used AI to process emails, but I didn&#x27;t want to send all my emails to an LLM, and the efficacy could vary over time, as the cat-and-mouse game of AI-spam versus AI-detection plays out. Cons: it does not prevent emails from landing in your Inbox in the first place, possibly triggering a notification. For me, this is OK because I use the gmail app on my phone and have it set to only notify for Important emails. Gmail is pretty good at recognizing unimportant emails, so when the emails that will be filtered first land, they most likely won&#x27;t trigger a notification It&#x27;s possible this will be over-inclusive, and I will be annoyed not to have seen a time-sensitive email about a conference I&#x27;m at, or some such thing. Time will tell, but so far I&#x27;m really glad to have these useless and frequent emails swept out of my Inbox. If you have found any other free&#x2F;innovative ways to get rid of AI-generated spam, please share! I&#x27;m sure there are better ideas than what I&#x27;ve come up with (and which Gemini wrote for me). I&#x27;ve included the Google script I use below. Note that you have to turn on the option (in Settings &#x2F; General) to automatically add email recipients to your Other Contacts. Create a new script at https:&#x2F;&#x2F;script.google.com using this for the body: function filterUnknownSenders() { &#x2F;&#x2F; Label to hold unknown emails for easy reviewing const LABEL_NAME = "Review&#x2F;Unknown"; let unknownLabel = GmailApp.getUserLabelByName(LABEL_NAME); if (!unknownLabel) { unknownLabel = GmailApp.createLabel(LABEL_NAME); } &#x2F;&#x2F; Find unread messages currently sitting in your primary inbox const threads = GmailApp.search("is:unread in:inbox", 0, 15); for (const thread of threads) { const message = thread.getMessages()[0]; const sender = message.getFrom(); const senderEmail = extractEmail(sender); &#x2F;&#x2F; Check if you have ever sent an email to this address const sentHistory = GmailApp.search(`to:${senderEmail}`, 0, 1); &#x2F;&#x2F; If you have NEVER emailed this person, archive and label the message if (sentHistory.length === 0) { thread.moveToArchive(); thread.addLabel(unknownLabel); GmailApp.markThreadUnimportant(thread); &#x2F;&#x2F; Prevents "Important" notifications Logger.log(`Archived unknown sender: ${senderEmail}`); } } } &#x2F;&#x2F; Helper to pull clean email address from "Name <email@domain.com>" sender strings function extractEmail(senderString) { const match = senderString.match(&#x2F;<([^>]+)>&#x2F;); return match ? match[1] : senderString; }

DTLifestyle & entertainment
Show HN
—

CodeConnect: Coding Agents on Your iPhone

Hi HN, CodeConnect is an iPhone app where you get to control your coding agents across multiple computers from anywhere. Install the daemon (on mac or a linux machine) and run "codeconnect claude" or "codeconnect codex" and its streams the session on the app. Runs over Tailscale and fully open-sourced. Would love some feedback :)

DTSoftware developmentDTAgent observabilityDTmacOS
Show HN
—

Make V2EX Clean Again，纯粹简单的内容屏蔽插件

市面上已经有了很多 V2EX 的插件，但是它们的功能太多，如果你和我一样，只是想屏蔽一些内容，但是又保持 一定粒度的控制，可以看看我的这个油猴脚本。 脚本只做好两件事：浏览、发帖。 1. 拉黑帖子的关键词后，可以设置三种模式：隐藏、折叠、模糊。 2. Base64 自动解码 3. 回复/发帖框预览与图片上传（支持移动端） 4. 所有的操作都在本地，数据不出浏览器。 电脑端效果： 手机端效果（需要先安装脚本管理器）： 下载地址： 之前的帖子：

Original
DTSkill / plugin
V2EX · I Made This
—

做了个给 2D 游戏用的 AI 精灵图生成器：一张角色图生成待机、攻击动画，直接导出精灵图和 JSON

大家好，距离上次发帖已经过去挺久了。原因是 7 月底，我又失业了，哈哈哈。 不过这次失业我到没有那么焦虑了，原因是通过这一年的折腾，副业还是有了点成果。 然后就是哪怕失业了，我跟朋友那边也在合作做一些游戏项目，目前有稳定的订单，虽然赚的不多，但是起码饿不死。 然后我最近几个月呢，也在打磨自己的全新的产品[SpriteCanvas]( )，一个给 2D 游戏做角色动画的工具。 起因是自己做小游戏：角色立绘用 AI 很快就能出，但一到“让它动起来”就卡住。逐帧手画不现实；用视频模型生成一段动画，又得自己抽帧、抠背景、对齐脚底、拼成图集、写每帧时长，一套下来比做游戏还累。SpriteCanvas 就是把这条链路做完，最后给你一张游戏引擎能直接用的精灵图。 ## 效果 一张参考图，生成待机和攻击动画（ 35 帧，透明背景）： 剑士三连击，38 帧： 技能特效也能单独生成，每个 6 帧、透明背景： 导出时可以勾“像素风”，每帧重绘到小像素网格上，整张精灵图共用一套 32 色调色板，帧与帧之间颜色不闪： ## 怎么用 1. 描述角色，或者上传你已有的角色图。一次出几张候选，挑一张。 2. 选动作：待机、行走、奔跑、攻击、跳跃是内置的，也可以自己写动作描述。所有动作都从同一个角色生成，造型不会跑偏。 3. 逐帧检查，选帧范围和帧数。 4. 导出 PNG 精灵图和 JSON 图集。JSON 是 Phaser 、PixiJS 能直接读的 JSON Hash 格式，带每帧时长和脚底锚点。 做完还能在内置试玩场里用键盘跑、跳、打几下，先看看手感： 首页就有一个能玩的示例场景，不用注册： 视频演示（ YouTube Shorts ）： ## 不用登录的免费工具 顺手做了几个小工具，都在浏览器里本地处理，不用注册： - [精灵图切片]( )：把一张精灵图切成单帧 - [GIF 转精灵图]( )、[精灵图转 GIF]( ) - [视频转精灵图]( ) 还有一套 [CC0 免费素材包]( )（苔藓骑士 5 个动作、剑士，加史莱姆、蘑菇怪、哥布林、石头巨人几个怪物和一组特效），可商用，拿去测试游戏代码也行。 ## 价格 - 邮箱验证后送 40 积分，7 天内有效；之后每天送 3 积分，最多攒到 12 ，免费积分只能用于标准画质。 - 每个任务开始前会显示要花多少积分；任务失败、没有产出时，积分会退回。 - 付费套餐 Starter 起步价 $12/月；也可以不订阅，单独买积分包。 ## 目前的不足 - 它不是逐像素的像素画编辑器。像素风是在导出时重绘的，单个像素还得去 Aseprite 这类编辑器里修。 - 动画是排队生成的，要等一会儿，不是秒出。 - Unity 、Godot 的导入流程还没正式验证。现在确定能直接用的是 PNG 精灵图加 JSON （ Phaser 、PixiJS 已验证）。 想听听大家的意见：你做游戏时最缺哪类动作或素材？想要哪个引擎的导出？用下来哪里卡住了？评论区或者站内反馈都可以，谢谢！

Original
DTSecurity & testingDTLifestyle & entertainment
V2EX · I Made This
—

分享最近做的两个小程序 - 心愿档案室 & 本地工具箱

1 、心愿档案室 起因是今年 6 月份身边的人突发恶疾，想着人生短暂，总有一些期待完成的事情会给人以希望。 2 、本地工具箱 这个工具很早就做了。最近经常坐火车，但是信号非常不好，加了几个娱乐工具。 当然也有一些实用工具，有 v 友需要的工具也可以酌情添加上去。

Original
DTLifestyle & entertainment
V2EX · I Made This
—

支持图片显示以及 ssh 的情况图片粘贴的跨平台终端

基于 Alacritty 的， 发现 windows 上好像号称支持 ssh 粘贴图片的终端都用不了，于是弄了一个 还支持显示图片，搭配 codex herdr 这种，走的 kitty 协议 支持 macos arm64 ，windows 10/11 ，linux x64 的 centos7.8 windows 上有一个内置浏览器以及 vnc 查看器 基本上按照自己的使用习惯弄的。

Original
LanguageRustDTSoftware developmentDTmacOSDTWindows
V2EX · I Made This
0

给 Tesla 做车衣涂装网站还蛮好玩的，不过这么一个小需求现在也这么卷了

在独立开发群里看到有人发了个网站， 玩了下感觉还挺好玩，然后深入看了下发现现在给 Tesla 做车衣涂装网站这么一个小需求也很卷了，随便搜一下就可以看到很多类似网站 ... 想请教一下这种是如何做出来的，我知道现在不用了解原理也可以让 AI 做出来，但我还是希望可以系统了解一下大概的原理是怎样的。

Original
DTSoftware developmentDTWeb appDTWeb
V2EX · I Made This
—

[分享创造] 让 agent 反复渲染比对，是我目前找到的最笨但最稳的办法

做图片转 PPT 最难的不是生成第一版，而是让第一版和原图对得上。 我的做法是让 agent 反复做同一件事：渲染成图、和原图逐块比对、找出最差的一块、改、再渲染。单张通常要十几轮。 笨的地方是慢，每轮都要真渲染，不能只看模型自述。稳的地方也是这里：差异是量出来的，不是猜出来的。 现在主要卡在两类图：超大图渲染慢，长条图分块后对齐容易错。前者在考虑分区降采样，后者在试按格拆页。 有没有人做过类似的渲染比对流程？想听听怎么控制轮数和成本。

Original
V2EX · I Made This
—
Still trending3 highlights⌄

16 repositories were already featured in the last 3 reports, so they are not repeated in today’s discoveries.

thedotmack / claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions.

LanguageTypeScriptDTSoftware developmentDTAgent extensionOriginalai
+1.7K stars today · seen in 1 of the last 3 reports

Donchitos / Claude-Code-Game-Studios

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

LanguageShellDTSoftware developmentDTAgent orchestrationOriginalai-agents
+1.3K stars today · seen in 1 of the last 3 reports

pbakaus / impeccable

The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

LanguageRustDTSoftware developmentDTAgent extensionOriginalagent-skills
+1.3K stars today · seen in 1 of the last 3 reports

DEV TRENDS / COMMUNITY

Discuss this edition

Sign in with GitHub to share a thought, question, or useful follow-up.

Open discussions ↗