Home / Browse
Inspect repositories, adoption requirements and practical uses of open-source tools.
732 public stories
V2EX ·
最近用 AI 做了一套企业级应用基础架构，包含身份认证、RBAC 权限管理、数据库、缓存和部署等能力。 项目地址： https://github.com/gvray/gvray-admin 做这个项目时，我一直在想一个问题： 以前前端转全栈，需要花不少时间学习后端技术。现在有了 AI ，能不能先借助 AI 完成一个完整项目，再通过理解代码、解决问题，逐步具备全栈开发能力？ 当然，代码能跑不代表工程质量过关。架构设计、安全性和可维护性，依然需要认真对待。 想听听大家的看法： 现在的 AI ，能让前端开发者真正跨过全栈开发的门槛吗？ 如果你来审查这个项目，会优先关注哪些问题？ 欢迎交流，也欢迎直接提 Issue 指出项目中的问题。
GitHub Trending ·
GitHub Trending recorded 1,187 stars in its daily window, observed Oct 30, 2026 (UTC).
Hugging Face Spaces ·
Interactive demo built with static
Hacker News ·
Submitted by sanmak. Hacker News recorded 4 points and 1 comments as of Oct 28, 2026 (UTC).
Hacker News ·
Submitted by pallavisingla. Hacker News recorded 1 points and 0 comments as of Oct 28, 2026 (UTC).
Hacker News ·
I run my business on four Claude Code agents: Titus, Pheme, Davinci and Metis. They write my newsletter, The AIgent (about 9k subscribers), every day through a drafting and proofreading engine that Pheme checks before scheduling. They also build AI courses, run a pipeline that turns the day's featured repo into a talking-head video of my avatar for Instagram, set up ad deals, and run Meta ads and email funnels with me. Nothing closes until I sign off. Metis posts jobs on a job board and the othe
Hacker News ·
Hi HN. Weir is for one problem: credentials crossing the boundaries of your AI agent. For agents you build, Weir plants fake credentials where real ones would live, runs the agent's normal flows, and checks what comes out: telemetry, logs, console output, model requests, and requests to other services. It looks for those exact values, including common encoded forms, and reports where they went without printing the credential. pip install weir-scan weir canary judge --sample That sample shows a p
Hacker News ·
Submitted by snipextt. Hacker News recorded 2 points and 0 comments as of Oct 28, 2026 (UTC).
Hacker News ·
Submitted by erogol. Hacker News recorded 4 points and 0 comments as of Oct 27, 2026 (UTC).
Hacker News ·
Submitted by ccheez34. Hacker News recorded 1 points and 0 comments as of Oct 27, 2026 (UTC).
Hacker News ·
Submitted by achardalias25. Hacker News recorded 1 points and 0 comments as of Oct 27, 2026 (UTC).
GitHub Trending ·
LIST OF ALL MY JAILBREAKS
GitHub Trending ·
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/ .
GitHub Trending ·
An agentic skills framework & software development methodology that works.
量子位 ·
人形机器人全套图纸开源！从关节到算法，下载就能自己造。
Hacker News ·
Submitted by deep_roiforce. Hacker News recorded 1 points and 0 comments as of Oct 27, 2026 (UTC).
GitHub Discovery ·
中文版 AI 姿势参考图库 · 1439 组 / 2878 张图片 / 完整汉化 · 零依赖静态画廊
GitHub Discovery ·
See how your app actually fits together. An interactive, plain-English map of your codebase, drawn by Claude or Codex.
Hacker News ·
Submitted by ermoluk. Hacker News recorded 1 points and 0 comments as of Oct 27, 2026 (UTC).
GitHub Discovery ·
🤖 Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through one Modelflare key. Reach them in the app, WeChat or Feishu; they remember you, work in the background, run commands and use your computer. Pay per use.
量子位 ·
OCR 3.0时代，来了
V2EX ·
最近我们做了一个新项目 LLMPod ，定位是开源的私有化 LLM 推理服务平台，目前正在招募首批体验用户。 做这个项目主要是因为自己部署大模型之后，会发现“把模型跑起来”其实只是第一步。 后面还有 GPU 节点管理、推理引擎、模型部署、API Gateway 、故障切换、API Key 、配额、调用日志以及多用户权限等一系列问题。 LLMPod 希望把这部分能力整合起来。 目前主要包括： 接入和管理自己的 GPU 节点； 可视化部署、管理模型； 支持 vLLM / SGLang 等推理引擎； 将模型发布为 OpenAI 兼容 API ； 统一管理外部模型 API ； API Key 、配额、用量及调用日志管理； 路由、权重和 Failover 。 开源自托管版本可以免费使用。 目前项目还处在比较早期的阶段，所以这次主要想找一些 真正有 GPU 服务器或者有多模型 API 管理需求 的朋友参与测试。 如果实际部署过程中遇到兼容性问题、Bug ，或者觉得产品设计有什么不合理的地方，都欢迎反馈。 官网： https://llmpod.ai GitHub： https://github.co
量子位 ·
开源一周，Github 拿下超 1000 star，X上关注度破百万，并登上 Today‘s news 推荐
V2EX ·
最近自己折腾了一个 iOS 阅读器，叫「小浣熊阅读」，现在开源了，想发出来和大家交流一下。 之前一直用香色闺阁看书，用得挺习惯。不过在我自己的使用过程中，搜书有时需要等比较久，后来能用的书源也越来越少。看到安卓「阅读」的书源一直有人维护，就想着能不能在 iOS 上用起来，于是开始慢慢折腾。 最开始只是希望能导入书源，搜书少等一会儿，读起来舒服一些。后面边用边改，缺什么就补一点，慢慢成了现在这样。目前自己在用，也还有不少地方需要完善。 项目用 Swift / SwiftUI 开发，支持 iPhone 、iPad ，系统要求 iOS / iPadOS 15.0 及以上，采用 GPL v3 开源。 GitHub： Aminark/legado-ios TestFlight： 点击加入小浣熊阅读公测 目前陆续补了这些功能： 书源导入和管理 ：支持 JSON 文件、URL 、二维码导入，以及书源分组、编辑和调试。 多书源搜索 ：多个书源并发搜索，结果陆续显示；做了有效书源优先、结果缓存和同书多源合并。 书架和阅读 ：支持书架分组、章节更新、换源、阅读进度、目录和书签。 排版调整 ：可以调整字号、
V2EX ·
最近在用 DeepSeek Harness（DSH）跑编码任务，写了一个 Discord 适配器插件，把整个会话面搬进了 Discord guild，手机上也能随时派活、看进度、批操作： https://github.com/addozhang/dsh-discord 简单说就是：在频道里 @ 一下 bot 说个任务，它会自动开一个 thread，回答实时流式渲染进去；过程中需要审批或澄清的问题会变成按钮消息，点一下就继续，不用回到电脑前。 主要功能： @mention 即会话 ：频道里 mention bot 提任务，自动开线程、流式渲染回复（打字状态、工具调用、finalize 都有） 审批/提问进 Discord ：权限切换、危险操作确认、agent 提问都以按钮形式出现在线程里，手机可操作 斜杠命令面 ：8 个命令（会话管理、项目绑定 guild、权限预设切换、模型选择等） 权限分级 ：guild 白名单 + member / workspace-admin / host-operator 三级授权 设置卡片 ：直接在 DSH web 的 Settings 里配置 bot to
Hacker News ·
Submitted by rajganesan-aroh. Hacker News recorded 1 points and 0 comments as of Oct 27, 2026 (UTC).
Hacker News ·
This is hardly a greenfield area. There are tons of agent-to-agent communication apps. But, at least to my taste, a lot of them are too complicated or too opinionated. If we learned anything from the HuggingFace incident, it's that modern AI agents don't need a lot of help communicating. They are smart and creative and figure it out. So...with that in mind, I (meaning I + claude and friends) built kashkeshet, or kkt. It's a small, Rust-based MCP server that gives agents a few simple chat primiti
V2EX ·
做 iOS app 的应该都遇到过：从浏览器复制的 App Store 链接带国家代码，比如 apps.apple.com/us/app/ ... 。发给其他国家的人，要么进的是美区页面，要么 app 在他那个区没上架，直接提示这个 App 在你所在的国家或地区不可用。 所以写了个小工具 Hither： https://hither.link/ 用法：粘贴任意国家的 App Store 链接或者 app ID ，得到 hither.link/<app id> 。 每次点击时： Cloudflare Worker 从请求里读访客所在国家（ request.cf.country ） 调 Apple 公开的 lookup 接口（ itunes.apple.com/lookup?id=...&country= ... ）查这个区有没有上架，结果在边缘缓存一天 有上架：跳到访客自己国家的商店页面 没上架：先试美区，再按英国、加拿大、澳洲、德国、日本等大区依次找，找到有上架的为止 踩到的一个坑：iPhone / iPad 上 App Store app 只能打开当前账号所在国家
Hacker News ·
Hi HN, I'm Alexander. Yes, this is another agent harness. Here is why I built one anyway. I was engineer #2 at Browser Use, where I built our agent harness and the evals behind it, including BU Bench, which became a default benchmark for browser agents. I left in September to build Mainplane. The problem: local agents die with your laptop, and cloud agents can't reach your work. Many cloud platforms ask you to "select a repository", but my work is not that simple. I work across a deskt
Hacker News ·
Submitted by Garbage. Hacker News recorded 1 points and 0 comments as of Oct 27, 2026 (UTC).