DevTrendsDeveloper trends
Accent color

DEV TRENDS / DAILY DISCOVERIES

Nov 1, 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 / 116

听笺

粘贴中英文文章或导入公众号链接，自动提炼 AI 文字要点，点击后生成语音，先听重点再听原文，支持倍速播放、七天账号记录和跨设备续听

Original
Chinese Indie Developers
—

Logo Animation AI

上传静态 Logo，选择动效模板或用文字描述效果，生成用于品牌展示、视频片头和社交媒体的 Logo 动画，无需掌握剪辑或关键帧

Original
DTContent creationDTLifestyle & entertainment
Chinese Indie Developers
—

Pic2SVG

上传普通图片（JPG/PNG 等），转成可编辑的 SVG 路径，浏览器本地运行、文件不上传，2 MB 以内免费无需注册，另附 SVG 结构检查器 - SVG checker

Original
Chinese Indie Developers
—

Big Walk Guide

Big Walk 非官方中英攻略，浏览器内信号码规划器、坐标查询与谜题 walkthrough，免费无需注册

Original
DTResearch & learningDTContent / resource
Chinese Indie Developers
—

Roam Radio

全球网络电台目录与播放器，按国家、音乐流派、语言或在 3D 地球上找台，浏览器直接收听，每个电台有独立详情页，免费无需注册

Original
DTData & operationsDTLifestyle & entertainment
Chinese Indie Developers
—

湾区 AI 日历

粤港澳大湾区 AI 活动与赛事日历，把深圳、广州、中国香港、东莞、珠海的 AI 大会、行业沙龙和黑客松按城市和日期排好，每天核对一次，每场都带主办方与官方报名入口，可一键订阅到手机日历

Original
Chinese Indie Developers
—

Magic Resume

Magic Resume is an open-source AI resume workbench: the AI proposes edits in place and you accept or skip each one. MIT-licensed core, 20 templates, six modes, cloud sync.

LanguageTypeScriptDTAgent extensionDTAgent orchestrationOriginalai
Chinese Indie Developers
102

ReferralCodes Canada

加拿大推荐码与注册奖励目录，查找、比较并分享各种服务的推荐码，了解奖励详情、资格要求和分享规则，帮助用户在加拿大获取更多优惠

Original
Chinese Indie Developers
—

AudioLens

Audio inspection & analysis extension for Visual Studio Code

LanguageTypeScriptDTSkill / pluginOriginalaudioOriginalaudio-analysis
Indie Dev · Programmers
67

claude-star-ipc：让 Claude Code、Codex 等不同厂商的 AI 编程终端分工协作

Cross-vendor LLM collaboration for Claude Code: let models from different companies (e.g. Opus + GLM) work as persistent peer terminals in one project — a dependency-free SQLite mailbox + role hook + installer (star topology, heartbeat push-wake, fan-out/broadcast). Unlike subagents / single-vendor agent teams.

LanguagePythonDTSoftware developmentDTAgent extensionOriginalagent-orchestration
Weekly Submissions
0

Buddy：让 AI 智能体帮你操作安卓手机

Android AI assistant in a floating bubble: Claude Code, Codex, OpenCode, Gemini (Antigravity CLI) or Grok use your phone for you — read the screen, tap, type. Runs on your own plan, open source, no root, no adb, no PC.

LanguageJavaDTAgent extensionDTWeb appOriginalaccessibility
Weekly Submissions
157

谁在招人？（2026年11月）

这里是免费的程序员招聘服务。 如果你们团队正在招人，欢迎把招聘信息发在这个帖子里面。请简要描述，岗位名称、工作地点、岗位要求、团队简介、联系方式等等。 发帖规则 请遵守以下规则，违者（很可能）被拉黑。 1. 同一团队招聘多个岗位，请写在一起，不要分成多个部分张贴。 2. 必须披露招聘公司的名称，禁止匿名招聘。 3. 谢绝中介和猎头发帖。 4. 不得发布与招聘无关的内容，且不得对公司或岗位进行评论或抱怨。 有意应聘的读者，请直接与发帖人联系。 历史帖 程序员的招聘往往长期有效，大家别忘了查看上月的岗位。 2026年：10月，9月，8月， 7月，6月，5月，4月，3月，2月，1月 2025年：12月，11月，10月，9月，8月，7月，6月，5月，4月，3月，2月，1月 2024年：12月，11月，10月，9月， 8月，7月，6月，5月，4月，3月，2月，1月 2023年：12月，11月，10月，9月，8月，7月，6月，5月，4月，3月，1月～2月 2022年：12月，11月，10月，9月，8月，7月，6月，5月，4月，3月，2月，1月 2021年：12月，11月，10月，9月，8月，7月，6月，5月，4月，3月，2月，1月 2020年：12月，11月，9月-10月，7月-8月，5月-6月，4月，3月， 1月-2月 2019年：12月，9月-11月，8月

Original
DTBusiness & growth
Weekly Submissions
—

DisconfirmAI：下结论前先找反面证据的投资研究网站

我是作者。DisconfirmAI 是一个投资研究和阅读网站，出发点是下结论之前先去找可能推翻自己判断的证据。 主要有这几块： 阅读：每天从公开来源整理 AI 与投资相关的信息，每条保留原文链接和日期，标注分成背景、存疑、编按三种，事实和观点分开写。 研究：可以对着财报和数据提问，回答里的数字注明口径，引用能点回原文，已核验和推测分开写。 雷达：把公司、主题或者自己写下的条件交给它定时扫描，有实质变化才提醒，没变化也会记一笔扫过了。 投资体系：用自己的话写下判断标准和认错条件，研究时按这套标准检查。 另外还有 AI 100 榜单和 AI 产业地图，不用登录就能看。 阅读和投资体系永久免费，注册送 400 积分，付费版每月 29 美元。网站只做研究辅助，不提供买卖建议。

Original
DTResearch & learningDTWeb appDTWeb
Weekly Submissions
—

Byteland：把开发者画成一座夜晚城市

Byteland 把每个开发者画成夜晚城市里的一栋楼：每个 GitHub 仓库是一个房间，最近 30 天有提交的仓库，窗户会亮灯。输入任何 GitHub 用户名，都能直接看到 TA 的楼，不需要注册。 用 GitHub 登录后可以装修自己的楼：选风格（东京、赛博朋克、布鲁克林……）、写滚动的 LED 招牌、在楼顶挂海报 每个项目都有一个房间：聊天、论坛和语音频道（语音点对点传输，不经过服务器） 个人主页 README 卡片： Markdown，不需要 token（生成页面： 也提供远程 MCP 服务： AI 助手搜索城市里的人和项目 整个城市用 Canvas 程序化绘制，没有前端框架、没有依赖；界面支持 17 种语言，包括中文 作者：@kaanisthatyou，来自土耳其的独立开发者。 🤖 Generated with Claude Code

Original
DTSoftware developmentDTAgent extensionDTWeb app
Weekly Submissions
—

Tunenoodle：浏览器 MIDI 编辑与节拍工具，附积分制音乐生成

我是 Tunenoodle 项目方，来做一次工具自荐，不是独立测评。它把浏览器里的音乐草稿编辑、节拍练习工具和积分制 AI 音乐生成放在同一个站点。 比较具体的用途： 只想调整一小段旋律、不想先安装完整编曲软件时，可以先用免费的浏览器 MIDI 编辑器整理音乐草稿。 听到一段节奏却不知道速度时，可以用 Tap Tempo 跟着节奏点击，估算 BPM，再用节拍器按这个速度练习。估算值适合作为起点，不代表所有录音都保持固定速度。 给短视频或播客构思配乐时，可以先确定节奏和大致风格，再尝试音乐生成；不要把“生成出来”直接当成已经适合成片，仍需检查音乐与对白是否冲突，以及当前套餐和使用条款。 免费 MIDI 编辑、Tap Tempo、节拍器与音乐生成是不同功能：音乐生成采用积分制并提供付费选项，不把整个产品说成永久免费。工具适合快速试想法和练习，不能替代完整 DAW 的录音、混音流程。 如果周刊认为有用，欢迎作为浏览器音乐工具参考；也欢迎指出操作上不清楚或不实用的地方。

Original
DTLifestyle & entertainment
Weekly Submissions
—

Obama Mic Toss AI：上传一张照片，生成慢动作甩麦视频

Obama Mic Toss AI Obama Mic Toss AI 是一个在线 AI 视频生成工具。上传一张照片，就能让照片中的人物出现在预设的舞台片段中：慢动作走向镜头，头也不回地将麦克风向后甩出，由工作人员接住。无需拍摄视频或编写提示词。 Obama Mic Toss AI 的主要功能 上传照片替换角色：主角需要一张照片；在较长版本中，还可以为两位同行角色各上传一张照片。未上传的角色保留模板人物。 选择片段长度：Obama Mic Toss Generator 提供 4 秒、10 秒和 15 秒版本。4 秒版只替换主角，较长版本支持最多三人同框。 下载成片：生成后可下载带有配乐的横屏 MP4 视频。网站称近期视频通常在几分钟内完成。 Obama Mic Toss AI 的核心特性 这个工具使用预设的 AI 舞台片段，用户只需选择人物照片和版本，不必自行处理运镜、慢动作或麦克风接住的镜头。Obama Mic Toss Template 中的场景和配乐是固定的，不能通过照片更换背景。 新账号提供可用于生成一个 4 秒版本的免费额度；较长版本需要更多额度。网站表示，生成失败时会退还所消耗的额度。上传照片前，也请确认已取得照片中人物的同意；分享视频时应标注其为 AI 生成内容。

Original
DTWeb appDTWeb
Weekly Submissions
—

Tiny Desk Outstanding AI：把你和朋友放进《Outstanding》桌前演出片段的 AI 视频工具

Tiny Desk Outstanding AI Tiny Desk Outstanding AI 是一款浏览器中的视频生成工具。上传照片后，它会将你和朋友替换进《Outstanding》桌前演出片段，保留原有的场景、镜头节奏和声音，生成适合手机观看的竖屏视频。 Tiny Desk Outstanding AI 的主要功能 自选出演阵容：主唱照片为必填；萨克斯、键盘和两位和声歌手可分别上传照片。未填写的位置保留原表演者。 选择视频长度：Tiny Desk AI 提供 4 秒、10 秒和 19 秒三种版本，输出带声音的 9:16 MP4。 直接下载分享：无需安装软件或编写提示词，选择角色、上传照片并生成即可。 Tiny Desk Outstanding AI 的核心特性 这款工具编辑的是固定演出片段，而不是重新生成一场演出，因此不同版本会沿用相同的镜头和音乐。新账号可用赠送积分体验一次 4 秒版本；较长版本需要相应积分，生成失败不扣费。 使用 Tiny Desk Outstanding 时，请只上传已同意参与的成年人照片。该项目是独立制作的工具，并非 NPR 或原表演者的官方产品。

Original
DTLifestyle & entertainment
Weekly Submissions
—

Diff Anything：在本机比较文件夹、PDF 和表格

我是 Diff Anything 的开发者 Martin Grüner，想向周刊推荐这款本地文件比较工具。 它适合这样的工作：备份后检查两个文件夹有哪些新增或修改的文件，核对两份表格的行与单元格变化，或者查看两版 PDF 的差别。还可以比较文本、代码、JSON、图片等文件。比较过程在本机完成，不上传待比较的文件，不使用 AI。 Mac 版可从官方商店免费下载。免费版每天最多新建 10 个比较会话，通常每侧文件上限为 5 MiB；集合结果预览前 100 项，PDF 预览前 3 页。Pro 是一次性购买，中国区当前显示 ¥168，可移除预览和会话限制，并开放导出、三方合并与文件夹同步等功能。 界面支持英语、德语和法语，目前没有中文界面。Mac 版要求 macOS 13 或更新版本。

Original
DTSoftware developmentDTmacOS
Weekly Submissions
—

拾价：支持 AI 导购的订阅比价平台

AI 订阅与卡网比价平台，说出需求，让 AI 帮你选。聚合 ChatGPT / Codex、Claude、Gemini 等代充或账号报价，对比价格走势、充值渠道与质保。AI-powered shopping and price comparison for subscriptions and accounts, with cross-shop offers, price history and purchase details.

Original
LanguageTypeScriptDTData & operationsDTWebOriginalai
Weekly Submissions
133

Ayakaleaf Pro：Overleaf Pro 全功能的开源版实现，支持自部署 (1.4k stars)

The ultimate open-source Overleaf extension and alternative: a free, self-hosted, drop-in replacement for Overleaf Community Edition with nearly all Pro feature—SSO, AI Assistant, Git(Hub/Lab）/ Dropbox sync, track changes, sandboxed compilation, Zotero, Mendeley and more. Formerly @Ayaka-notes Overleaf Pro. Docs:

LanguageJavaScriptDTResearch & learningDTData & operationsOriginalai
HelloGitHub Submissions
1.5K

Novapod B300, B200, and H200 are on the live list. The GPU rental price is the ask on the card. Deposit USDT, USDC, SOL, or ETH and pay for the seconds the pod runs.

B300, B200, and H200 are on the live list. The GPU rental price is the ask on the card. Deposit USDT, USDC, SOL, or ETH and pay for the seconds the pod runs. 亮点 B300, B200, and H200 are on the live list. The GPU rental price is the ask on the card. Deposit USDT, USDC, SOL, or ETH and pay for the seconds the pod runs.

Original
DTSoftware developmentDTContent / resource
HelloGitHub Submissions
—

agent-qa：带持久记忆的自然语言测试工具

Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.

LanguageTypeScriptDTSoftware developmentDTAgent extensionOriginalai-agents
HelloGitHub Submissions
915

cjpais / Handy

A free, open source, and extensible speech-to-text application that works completely offline.

LanguageRustOriginalaccessibilityOriginalcross-platformOriginalspeech-to-text
GitHub Trending
36.4K

kornia / kornia

🐍 Geometric Computer Vision Library for Spatial AI

LanguagePythonDTResearch & learningDTData & operationsOriginalartificial-intelligence
GitHub Trending
11.7K

beenuar / AiSOC

Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.

LanguagePythonDTSecurity & testingDTAgent extensionOriginalagentic-ai
GitHub Trending
6.1K

hyprwm / Hyprland

Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.

LanguageC++
GitHub Trending
39.3K

Evil0ctal / Douyin_TikTok_Download_API

🚀 自托管的抖音、TikTok、B 站数据采集与无水印视频下载 API，支持 AI agent 通过 MCP 调用与离线语音转文字，Docker 一键部署。| Self-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI agents, CLI and web console, plus offline speech-to-text for downloaded videos. Self-healing identity pool, PostgreSQL archive, one docker compose up.

Original
LanguagePythonDTData & operationsDTLifestyle & entertainmentOriginalbilibili
GitHub Trending China
21.1K

xifangczy / cat-catch

猫抓 浏览器资源嗅探扩展 / cat-catch Browser Resource Sniffing Extension

Original
LanguageJavaScriptDTSkill / pluginOriginalchromeOriginalchrome-extension
GitHub Trending China
22.7K

forthespada / CS-Books

🔥🔥超过1000本的计算机经典书籍、个人笔记资料以及本人在各平台发表文章中所涉及的资源等。书籍资源包括C/C++、Java、Python、Go语言、数据结构与算法、操作系统、后端架构、计算机系统知识、数据库、计算机网络、设计模式、前端、汇编以及校招社招各种面经~

Original
DTResearch & learningDTData & operationsOriginalalgorithms
GitHub Trending China
27.8K

soybeanjs / soybean-admin

A clean, elegant, beautiful and powerful admin template, based on Vue3, Vite7, TypeScript, Pinia, NaiveUI and UnoCSS. 一个清新优雅、高颜值且功能强大的后台管理模板，基于最新的前端技术栈，包括 Vue3, Vite8, TypeScript, Pinia, NaiveUI 和 UnoCSS。

Original
LanguageTypeScript
GitHub Trending China
15.2K

agentmash

open-source multiplayer AI for teams' coding agents

DTSoftware developmentDTAgent extensionDTSkill / plugin
Product Hunt
116

Raah.dev

Track your revenue, analytics, and website performance

DTData & operations
Product Hunt
82

Click

Managed agents API that works with any model

DTData & operationsDTAgent observabilityDTWeb
Product Hunt
96

Termy

Your coding agent, in the notch

DTSoftware developmentDTContent / resourceDTTerminal
Product Hunt
73

magpie

everything you’ve saved, in one visual library

DTLibrary / SDKDTWeb
Product Hunt
91

HackerBooks – HackerTube, but for books mentioned on HN

Saw Karpathy's HackerTube and wanted the same thing for books. So I had Claude build one (Opus 5.5). It's ~16.5k books that at least two different HN commenters brought up, from 2007 till now. Each book links back to the comments that mentioned it. Data is downloadable from the about page. To be clear: Claude wrote almost all of it, including the data pipeline and the site. I mostly steered and made calls, bought the domain name, etc. It counts mentions, so it's not perfect (praising a book and trashing it both count). If your favourite book is missing or matched to the wrong thing, tell me.

DTResearch & learningDTContent / resource
Show HN
—

NES Contra (1987) port (ASM –> C and then C –> WebAssembly)

Based on vermiceli's annotated disassembly of Contra: https://github.com/vermiceli/nes-contra-us . Thanks for the great work. I ported it in two steps. First to C: the game logic is translated routine by routine from the 6502 assembly, and checked frame by frame against the original in the Mesen emulator. Then the C code to WebAssembly so it runs in the browser. The cherry on top: online multiplayer, so two players can play co-op over the internet. Source: https://github.com/epoyraz/nes-contra-us

DTLifestyle & entertainment
Show HN
—

BBRouter – Ben Eater's 8-bit computer, simulated on 3D breadboards

Hi HN, I kept wiring Ben Eater's 8-bit computer wrong, so I built a realistic virtual breadboard editor. Some of the nice features are side-by-side diff, scope, schematics auto-sync, auto-router (BBRouter stands for breadboard router), and my favorites: upload from the real Arduino IDE and connect to your AI with MCP, let Claude & co build it or help you troubleshoot. The link is the SAP-1 running. You can orbit it, probe a hole with the scope, slow the clock down, play with the virtual displays for debugging, then you can actually build it following the step-by-step instructions. A side-goal is to create a community, there are quite a lot of simulators out there but mostly offline / too abstract to realistically use it for a real build. I also never found one that had a decent UI/UX and worked well on mobile or with a trackpad. Happy to answer anything, and tell me what breaks. p.s. Maker plan is $7/month; code HACKERNEWS makes the first month free and then $5/month for as long as you keep it.

DTSoftware developmentDTAgent extensionDTMCP service
Show HN
—

Jointter – A daily word puzzle using dots and lines

Hello everyone. I’m a mathematician by training, and I love mathematical and logical puzzles and brain-teasers. Inspired by popular games like Sudoku and Wordle, I decided to come up with an engaging game of my own. As it turns out, that’s not so easy! I had a few ideas, but beyond the core mechanics, a game also needs to be interesting and easy to explain — after all, nobody (including me) wants to spend a long time reading through rules. Let’s start with the concept, which came to me quite spontaneously: what if we represented letters like the digits on a digital clock — using lines, with dots at the points where those lines intersect? For instance, the letter "E" would consist of four lines and six dots — three at the intersections and three at the ends of the lines. It turns out that every letter of the Latin alphabet can be represented this way (with a minor caveat) using three rows of dots connected by some lines. This immediately presented a challenge: how do you represent O-shaped parts, like those found in "B", "O", or "R"? I decided not to use O-shapes, an use onl rectangles/squares. This "alphabet" is always displayed below the game board, so the player can see the letters. The goal of the game is simple: you are presented with three rows of dots and a set of lines, and you have to figure out the word. A great feature of the game is that it’s possible to deduce the word in a single turn — all the necessary information is right there on the board, allowing you to arrive at the answer with certainty. And what if you can’t figure it out on the first try? You can enter a guess, much like in Wordle: if the lines from the entered word are part of the target word, they turn green; if not, they turn red. The same applies to the dots. As you play, more and more lines gradually appear... Why provide some lines at the start? To uniquely identify a specific word — or a small set of words — from the dictionary. For example, you could select a configuration of lines that corresponds to only one word, like "RADIO", or perhaps to just two possible words, such as "WEIGH" and "WRONG". The rules seem clear, but the mechanics — not so much. There are dots on the board; when I enter a word, I realize there aren't enough dots. What should I do? Initially, if the target word had 5 letters, I allowed users to enter 4- or 5-letter guesses, but that just confused players. So, I came up with a different solution: adding red dots for dots that aren't part of the target word. Another drawback is that the game is somewhat skewed. Since letters are processed from left to right, the first letters are revealed more frequently than the last ones. Then there’s the game design itself: should the target words be 5 letters long, or 6? Should a single board allow for multiple possible answers (like "WEIGH" and "WRONG"), or should it be limited to one — or perhaps more than two? Should the difficulty increase from Monday to Sunday? Currently, it’s set up this way: Monday is the easiest (a few 3-letter words), while Sunday is the hardest (more than two 7-letter words). The tech stack is simple: I use Flask for the backend and Python for the algorithms; I wrote the algorithms myself. While the JS, HTML, and CSS were created with the help of AI. I’d love for you to test the game and share what you like, what you don’t, and what could be improved. Specifically, I’d like to know: 1. Is the game and its goal clear? 2. Is it fun to play, and what could be improved? 3. Would you share it with your friends? I welcome any constructive criticism. You can find the game at https://www.jointter.com/ It’s free and requires no registration. Thank you very much.

DTLifestyle & entertainment
Show HN
—

Vela, a New Linux Desktop Environment

Hi, take a look at this. I didn't like KDE nor KDE Themes, so I made Vela, a new stacking desktop environment, and even though this is not very inspired in terms of aesthetic, this is not the point of Vela (not yet). Point of Vela is mostly architecture: Vulkan 1.4 only, no OpenGL fallback; based on wlroots, but has a custom renderer. GPL3 license. Vela is currently at 0.1.0 beta after one month of Alpha testing. Tested and working both on AMD and Nvidia. Requirements: a GPU and driver with Vulkan 1.4 support. I’m looking for people to try it on their hardware and report issues, and for contributors. Thanks code: https://github.com/vela-desktop/vela

DTLinux
Show HN
—

Haris list jobs board for agents

Access the trial via MCP Can be used to advertise services and strike deals. Please send feedback via email or otherwise Thank you

DTAgent extensionDTMCP serviceDTContent / resource
Show HN
—

I made a game about the 3k-year evolution of Chinese characters

I've always found it fun to explore the history of Chinese characters. Some modern characters are unrecognizable from what they represent, while others still look similar to the versions carved in turtle shells over 3,000 years ago! I built a Heardle-inspired game where you guess the meaning of a Chinese character as it gradually transforms back through time to a more pictographic version. Let me know what you think.

DTLifestyle & entertainment
Show HN
—

Create a Dumbphone on Android

Beeswax blocks web browsers, newly installed apps and any app you pick until you enter your lock code. Open source, no network access, one permission.

DTData & operationsDTWebDTAndroid
Show HN
—

Dirtbound | Free 3D Browser Rally Game

Experience high-octane rally racing with [Dirtbound]( ), a thrilling 3D browser racer featuring realistic vehicle dynamics, procedural dirt tracks, and global daily challenges. Master precision drift control and conquer tough gravel stages in the free [Dirtbound game]( ) right in your browser with zero downloads!

DTLifestyle & entertainmentDTContent / resource
V2EX · I Made This
—

给开源 AI 雷达做了 WorkBuddy 技能，想把选型从名单变成可核查记录

之前做了 AI 开源项目雷达，这次把研究与选型流程适配成 WorkBuddy 技能「开源 AI 项目研究与选型」，已审核上架。 主要解决一个小问题：问 AI“帮我选个知识库”时，容易得到几个名字，但硬条件、偏好和证据缺口常混在一起。 可以直接这样问： “帮我选自托管中文知识库，Docker 和 Web 界面必须具备，低代码只是偏好。关键能力给来源和数据时点；找不到匹配就说明，不要偷偷放宽要求。” 也可以比较指定候选、核对许可证据、找替代方案，或整理待验证的候选技术栈。输出区分事实、建议、未知项与风险，不把 Star 当适用性，不替你安装或执行仓库。 我是开发者，使用的是公开数据，原有实现公开可获得； WorkBuddy 版提供平台内适配。购买不含 WorkBuddy 积分或网站会员，费用和条件看当前平台页面。以上是使用问法，不是已经跑出的测试结果。 技能详情： [查看「开源 AI 项目研究与选型」 WorkBuddy 技能详情]( ) 本文由 AI 辅助整理。

Original
DTResearch & learningDTSoftware developmentDTWeb app
V2EX · I Made This
—

做了个 AI 说唱视频生成器：传一张照片，出一段对口型的 Rap 表演（免费预览，单条 $3.99）

一直觉得「真人出镜说唱」这类内容在短视频端很火，但普通人做不了：不会写词、没有 beat 、更不敢出镜唱。于是做了这个一站式的： - 传 1–2 张照片（或只输入一个主题），选一个舞台模板，出一段 12 秒对口型说唱视频 - 歌词可以自动写（给个主题就行），也可以自己填 - 人声是 AI 说唱声音，beat 是 AI 原创的——我们不碰任何版权歌曲，这是产品红线；用户可以上传自己拥有的音频 - 模板：diss track 、生日、节日、圣诞 rap 、圣诞老人定制视频、双人 battle 商业模式：单次付费，不搞订阅。免费账号每段 6 秒带水印预览，一条 480p 成片 $3.99 。 站上还有个免费的 AI roast 生成器（ playful / savage / rap battle 三档火力），生成的 roast 可以一键丢给 diss track 生成器做成视频，欢迎先玩这个： 主站： 求反馈：口型同步的自然度、价格感知、还想看什么模板。

Original
V2EX · I Made This
—

做了个 Mandem in Disguise AI 小工具：上传照片，生成单人 / 双人闪光变装视频

大家好，分享一下我们做的小网站：Mandem in Disguise AI 。 它做的是一种短视频变装效果：先是日常穿搭，镜头闪一下，再变成黑色头套和羽绒服的造型。我们把选参考视频、上传人物照片、生成和下载放在了一个页面里，不用自己拼提示词。 目前有三种模板： - 单人变装：上传一张单人照。 - 双人镜子自拍：左右各上传一张单人照，右边的人对应拿手机的位置。 - 双人近景闪光：同样是两张独立照片，分别对应后方左侧和前景右侧。 双人版本不需要两个人先拍一张合照。选好模板后可以先看参考，再按左右位置放照片；支持 Google 登录，完成后可以在账户里查看任务并下载 MP4 。页面也有中文版本。 这里也说清楚边界：页面里的预览是模板参考，不是用户上传照片后生成的成品。底层用参考视频配合人物照片做生成式编辑，面部细节、动作和声音可能出现偏差，不是每一帧都精确替换的传统换脸。照片请使用本人或已取得同意的成年人照片。 想请 V 友帮忙看看：双人的左右位置说明是否直观？从选模板到上传照片，有没有让人看不懂的地方？如果做这类短视频，你更想要哪种构图或变装模板？ 欢迎直接提问题和建议。

Original
DTWeb appDTWeb
V2EX · I Made This
—

吃灰近 10 年的域名被我拿出来做了个小项目:HYB

2016 年的 6 月份时候买了不少的.vip 后缀的域名,后来价格跌了,基本上低价处理了,亏的一塌糊涂,有没有经历这个事情朋友啊.就给自己留了一个,一直在放着吃灰. 前几天为了加外链涨 DR,找了不少的产品提交平台,一份份的提交,还专门做了个表格.用表格有点麻烦,于是就启用了我那个吃灰将近 10 年的域名做了这个 HYB 项目. 项目很简单就是把我之前用表格做的事情搬到线上来处理了.我自己用着还比较顺手,就来 V2EX 想发个帖子,请大家帮忙给点评点评.出出主意. 感悟一下:说实在的当时留的这个域名,真的没有想到能持有这么久,知道的行情的人应该懂得,这个后缀价格一路下跌,就没有反弹过.不知不觉拿着快 10 年了,你别说,还真有点小感情来.现在把它做成一个小项目,也算是一种妥善的交代吧. 致敬,感谢.

Original
V2EX · I Made This
—
Still trending3 highlights⌄

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

pingdotgg/t3code

No project description yet.

LanguageTypeScriptDTSoftware development
+3.1K stars today · seen in 1 of the last 3 reports

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
+1.5K 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
+970 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 ↗