标签：#opensource

The short answer is: while OpenAI Sora offers unmatched visual quality and physics rendering, it remains restricted behind a paid subscription structure. For creators who want a completely free, unlimited AI video generator, the newly released open-source LTX Desktop app by Lightricks allows you to run the LTX-2.3 video model locally on your own computer with zero usage costs or filters. The AI Video Paywall Frustration If you have tried building AI video content for YouTube, TikTok, or social marketing, you know how expensive it is. Platforms like Runway Gen-3 and Luma Dream Machine charge by the second. A simple five-second clip can cost up to fifty cents in API credits, making creative experimentation almost impossible for solo developers. OpenAI Sora is a powerhouse, but its high computational overhead means it will likely remain a premium, paid tool for the foreseeable future. To bypass this, our dev team set up the new open-source LTX Desktop application on our local workbench to see if local video generation is actually viable for production. Here is our hands-on review. |---|---|---|---| | OpenAI Sora | Closed Cloud | None (Paid Plan) | Cloud-Only | Cinema-grade physics, long multi-action shots. | | Runway Gen-3 | Closed Cloud | Daily Free Credits | Cloud-Only | Cinematic camera pans, high texturing quality. | | Wan2.1 | Open Weights | Free Hugging Face Spaces | 16GB VRAM (Local) | Photorealistic human movement, natural lighting. | | LTX-2.3 | Open Weights | LTX Desktop (Free) | 8GB VRAM (Local) | Fast generation speeds, local desktop interface. | Running Video Models Locally: The LTX Desktop Solution LTX Desktop, developed by Lightricks, is a standalone, open-source desktop application that lets you run their LTX-2.3 video generation model on consumer-grade graphics cards. Why LTX Desktop is a Game-Changer Low VRAM Footprint: Unlike HunyuanVideo or Wan2.1 which require massive 16GB-24GB VRAM cards to compile locally, LTX-2.3 is highly optimized and runs com

The first hour with a new repo is archaeology: open package.json , skim the Makefile, hunt for .env.example , grep workflows for secrets. , check Compose for ports. I already built focused tools for each of those questions. What I still wanted was one command that prints the whole map. coldstart coldstart is that overview — offline, no accounts, agent-friendly JSON. go install github.com/SybilGambleyyu/coldstart@latest coldstart coldstart -md >> ONBOARDING.md coldstart -json It reports: Runtimes — Node engines, Go version, Cargo edition, Python requires, .nvmrc , .tool-versions Run — preferred npm scripts, Makefile ## targets, just, Taskfile Ports — Compose, env *_PORT , script --port Env keys — from .env.example CI secrets/vars — from GitHub Actions workflows (builtins like GITHUB_TOKEN omitted) Overview vs drill-down Need Tool One-pager coldstart Full task map howrun Every port + live check projports Secrets vs gh secret list needsecrets Lockfile PR summary lockbrief Typical first hour: coldstart # then only if you need depth: howrun -f test projports -unique -check needsecrets -check Small binaries, MIT, no SaaS. If it saves a README scroll, it is working.

Hey everyone! 👋 First of all, thank you so much for all the support, feedback, and feature suggestions since the Product Hunt launch. Every comment has been incredibly valuable, and I've already started implementing some of your ideas. Today I'm excited to share a new update to Rizzzler ! 🌙 ✨ What's New? 🎨 2 Brand-New Themes I've added two new themes , giving you even more ways to personalize your profile and match your own style. Whether you prefer something clean, vibrant, or expressive, there's now even more variety to choose from. 👀 Live Preview Panel One of the most requested improvements is finally here! You can now preview your showcase page while editing it . No more guessing how your profile will look after saving—see your changes in real time before publishing. 🎵 Audio Preview Choosing background music is now much easier. Instead of selecting tracks blindly, you can now preview audio directly before applying it to your profile. ✨ Profile Picture Decorations Want your profile to stand out even more? You can now add Profile Picture Decorations to give your avatar a unique look and make your showcase even more personal. More decoration styles will be added in future updates! ❤️ Thank You The feedback from the GitHub community and Product Hunt has been incredibly helpful. Many of these improvements came directly from community suggestions, and I'll continue building Rizzzler based on your ideas. If you have feature requests, bug reports, or suggestions, I'd love to hear them! 🔗 Try Rizzzler Website https://rizzzler.onrender.com Product Hunt https://www.producthunt.com/p/rizzzler-show-yourself-off GitHub https://github.com/DeveloperPuneet/Rizzzler-Stable Thank you for supporting Rizzzler! 🚀

FROST-SOP V6.1.0 工程实践：从初始化流水线看「零门槛上手」 作者：神通说 日期：2026-07-21 主题：周二·SOP工程 | V6.1.0 新特性深度解析 开篇：一个让所有开发者头疼的问题 想象这个场景： 你刚克隆了一个开源项目，兴冲冲地跑起来，结果： ModuleNotFoundError: No module named xxx ImportError: DLL load failed OSError: [WinError 2] 系统找不到指定的文件 你开始疯狂搜索、提问、等回复。一小时过去了，项目还没跑起来。 这是开源项目最大的痛点之一：「最后一公里」问题。 今天，我们来聊聊 FROST-SOP V6.1.0 是如何解决这个问题的。 V6.1.0 核心特性：初始化流水线 V6.1.0 版本最核心的更新，是一个 全自动初始化流水线（Initialization Pipeline） 。 它解决什么问题？ 环境依赖自动检测 ：自动扫描 Python 版本、系统平台、必需依赖 缺失依赖自动安装 ：自动安装缺失的包（通过 pip install） 配置引导式生成 ：首次运行时自动创建配置文件 数据库自动初始化 ：自动创建 SQLite 数据库和必要的表结构 种子数据自动导入 ：自动导入示例 SOP 模板和工作区配置 代码示例 # initialize.py - 初始化流水线核心实现 import subprocess import sys import os from pathlib import Path class InitializationPipeline : """ FROST-SOP 初始化流水线 """ def __init__ ( self , project_root : Path ): self . root = project_root self . issues = [] self . warnings = [] def run ( self ) -> bool : """ 执行完整初始化流程 """ steps = [ ( " 环境检测 " , self . _check_environment ), ( " 依赖安装 " , self . _install_dependencies ), ( " 配置生成 " , self . _generate_config ), ( " 数据库初始化 " , self . _init_database ), ( " 健康检查 " , self . _health_check ), ] print ( " 🚀 FROST-SOP 初始化流水线启动 \n " ) for name , step_fn in steps : print ( f " 📦 { name } ... " ) try : result = step_fn () if not result : self . issues . append ( f " { name } 失败 " ) print ( f " ❌ { name } 失败 \n " ) return False print ( f " ✅ { name } 完成 \n " ) except Exception as e : self . issues . append ( f " { name } 异常: { e } " ) print ( f " 💥 { name } 异常: { e } \n " ) return False self . _print_summary () return True def _check_environment ( self ) -> bool : """ 检查 Python 版本和系统环境 """ version = sys . version_info if version . major < 3 or ( version . major == 3 and version . minor < 10 ): self . issues . append ( f " Python 版本过低: { version . major } . { version . minor } " ) return False print ( f " Python { version . major } . { version . minor } . { version . micro } " ) return True def _install_dependencies ( self ) -> bool : """ 安装项目依赖 """ req_file = self . root / " requir

Introducing vernLLM: A Resilience Layer for LLM Applications Building production-ready LLM applications is not just about sending prompts and receiving responses. Real-world AI systems need to handle timeouts, provider failures, rate limits, inconsistent outputs, and reliability issues. That is where vernLLM comes in. vernLLM is a lightweight resilience layer for OpenAI-compatible chat completion APIs , providing a single interface with built-in retries, timeouts, circuit breaking, caching, structured output, and usage tracking. Instead of rebuilding the same reliability features for every LLM project, vernLLM gives you the tools needed to make your AI integrations more robust from the start. Features Automatic retries with backoff Transient failures happen. vernLLM automatically retries recoverable errors while failing fast on validation errors and non-retryable responses. Timeouts & cancellation Prevent hanging requests with configurable timeouts and cancellation support. Circuit breaker protection Automatically stop sending requests to failing providers and recover when the service becomes healthy again. Structured output with type safety Pass a Zod schema and receive validated, typed results back. const result = await llm . call ({ systemPrompt : ' Return JSON: { "skills": string[] } ' , userContent : ' Extract skills from: ... ' , schema : SkillsSchema // zod schema }); Provider-native JSON Schema support Constrain model generation itself instead of only validating responses afterward. Built-in caching support Cache LLM responses using your own cache adapter with cachedCall and cachedLLMCall . One interface across providers Use the same API across multiple providers: OpenAI Groq Mistral DeepSeek Cerebras Together AI Fireworks AI Ollama Anthropic Gemini AWS Bedrock Any HTTP-compatible provider through fromFetch Why vernLLM? Many LLM applications end up creating their own wrappers around provider SDKs to handle: retry logic API failures provider switching respons

I had a website blocker, a Pomodoro timer, a tab suspender, and a time tracker installed at the same time — four separate extensions, four separate settings pages, none of them talking to each other. Starting a focus session meant manually turning on the blocker, then starting the timer, and neither knew the other existed. So I built TabInsights , which does all four and actually connects them. What it does Website blocker — block by domain, category, or schedule, with an optional typed "unblock challenge" for the days willpower isn't enough. Pomodoro focus timer — one click starts a 15/25/45-minute sprint, which also auto-blocks distracting categories for the duration and unblocks them automatically when it ends. This is the part that actually solves my original problem — the timer and the blocker are the same feature, not two extensions coincidentally running at once. Memory saver — auto-suspends tabs you haven't touched in a configurable window (15–60 min), freeing roughly 50MB of RAM each via chrome.tabs.discard() . Suspended tabs stay in your tab bar and reload exactly where you left off with one click. Automatic time tracking — logs time per domain with no manual start/stop, and shows a daily focus score. A few implementation notes Manifest V3 removed persistent background pages, which meant every "ongoing" feature — sprint timers, the daily summary, auto-suspend checks, license re-validation — had to be rebuilt on chrome.alarms instead of a long-lived timer. The gotcha: Chrome clamps alarm intervals to a minimum of 1 minute in packaged (published) extensions, so anything needing finer granularity has to accept that floor rather than fight it. The blocker uses declarativeNetRequest — you hand Chrome a set of match rules and it enforces them at the browser level. The extension never actually reads the blocked request; it can't, by design, which is also the honest answer any time someone asks whether a blocker "sees" their browsing. The bigger architectural deci

GitHub热门项目 | Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform. | Stars: 4,671 | 190 stars this week | 语言: JavaScript

GitHub热门项目 | 猫抓 浏览器资源嗅探扩展 / cat-catch Browser Resource Sniffing Extension | Stars: 20,754 | 214 stars this week | 语言: JavaScript

GitHub热门项目 | Self-hosted AI coding assistant | Stars: 33,768 | 13 stars today | 语言: Rust

GitHub热门项目 | Free, open-source web app for learning about ontologies and Microsoft Fabric IQ. Explore a catalogue of pre-built ontologies, design your own visually, export as RDF/XML, and share interactive diagrams. Zero backend, fully static. | Stars: 1,549 | 487 stars today | 语言: TypeScript

GitHub热门项目 | Self-hosted deployment platform | Stars: 4,014 | 1,719 stars today | 语言: TypeScript

GitHub热门项目 | MCP server for interfacing with Godot game engine. Provides tools for launching the editor, running projects, and capturing debug output. | Stars: 4,810 | 25 stars today | 语言: JavaScript

GitHub热门项目 | 一个人人都能部署的基于 js 的弹幕 API 服务器，支持爱优腾芒哔咪人韩巴狐乐西埋帆弹幕直接获取，兼容弹弹play的搜索、详情查询和弹幕获取接口规范，并提供日志记录，支持vercel/netlify/edgeone/cloudflare/docker/hf等部署方式，不用提前下载弹幕，没有nas或小鸡也能一键部署。 | Stars: 2,789 | 13 stars today | 语言: JavaScript

GitHub热门项目 | A cross-platform, customizable science fiction terminal emulator with advanced monitoring & touchscreen support. | Stars: 44,986 | 8 stars today | 语言: JavaScript

GitHub热门项目 | 🚀 The fast, Pythonic way to build MCP servers and clients. | Stars: 26,378 | 77 stars today | 语言: Python

I've just published a small npm package called @modyra/core that came out of a very specific pain: handling "slightly complex" app state in frontend projects without ending up with a mess of context, custom hooks and scattered stores. The focus of the package is: Minimal API, all in TypeScript, no hidden magic No heavy runtime: just tools to model the core of your app as a set of state modules Designed to plug into React/Angular/vanilla JS without forcing you to rewrite everything The idea is to treat your app's domain as a set of "core units" with clear responsibilities: each unit exposes state, actions and rules, and the rest of the app simply consumes them. It came out of a few projects where Redux/Zustand/signals etc. were fine, but started to feel either too verbose or not very close to the actual business domain. If you feel like taking a look and tearing it apart, feedback (including harsh ones) is very welcome: naming, API design, examples - everything is still fresh enough to change. And if you think the approach is worth exploring, a star on GitHub would really help me keep pushing the project forward.

Liquid syntax error: Variable '{{% raw %}' was not properly terminated with regexp: /\}\}/

Cross-posted from the Loopress docs Loopress is a toolset to make WordPress reproducible and reviewable via Git . Versioned snippets, Composer without SSH, and more coming... Check Loopress WordPress doesn't have a package manager. If you want a PHP library in your project, be it Guzzle for HTTP calls or a PDF generation library in a snippet, you're either vendoring the code by hand or running Composer somewhere the WordPress admin can't see. We built a feature to fix that: a Composer UI inside the WordPress admin. Search Packagist, install a package, audit it for known vulnerabilities, all without SSH access ( full walkthrough here ). Before shipping it, we asked the wordpress.org plugin review team whether it would be acceptable in the official directory. The answer was no. The rule Here's the relevant line from Guideline 8 of the wordpress.org plugin directory: "Plugins may not send executable code via third-party systems." Installing a PHP package from Packagist is, by definition, downloading executable code from a third party and writing it to disk. It doesn't matter that our plugin never calls the installed code's autoloader itself, that the user has to load it deliberately from their own snippet. The review team was clear: the indirection changes nothing. The mere presence of that capability is enough to trigger the rule, whether or not it's ever used. There's no folder you can hide it in that makes it acceptable, they weren't shy about saying that outright. If you want PHP dependencies in a plugin distributed on wordpress.org, the only accepted path is to vendor them at submission time: ship the code, with a compatible license and readable source, not fetch it dynamically. For us, that meant Composer package management could never live in the same plugin that ships on wordpress.org. Full stop, no clever workaround changes that. What we tried first, and undid Our first move was the obvious one: split into two plugins. A "Core" plugin with snippet sync, distri

I watched my sister paste a CSV into on of our LLM overlords and ask a question then reword it and get a different number. That's the problem with letting an LLM both read your question and trust it's math. ADA splits the two jobs. Drop in a CSV or Excel file, get a dashboard, anomaly detection, a forecast, and plain-English answers, all calculated locally using pandas (locally in the sense of never leaving the server and going to the AI apis.). The LLM layer that you can use (it's optional) but that only sees column names and never your rows, and the whole thing works with zero API key if need be (not the LLM part of course). MIT licensed, solo-built, open to contributors (in fact would need help to make it move out of LLMs and have a few open issues). I wish to make it as LLM free as possible as I want to make it deterministic. Live demo: automated-data-analyst.streamlit.app Repo: https://github.com/saineshnakra/automated-data-analyst

FROST 深度：为什么 AI Agent 需要「家族谱系」？ 前言：一个古老的管理学问题 你有没有想过，为什么人类社会的组织方式大多是「层级制」？ 从部落、到王国、到现代公司，我们习惯了一种结构： 有人决策，有人执行，有人监督 。 但当我们构建 AI Agent 系统时，为什么大多数框架都把 Agent 做成「孤岛」？每个 Agent 有自己的记忆、自己的工具、自己的行为逻辑——像一个没有家族传承的独立个体。 FROST 的核心理念是：Agent 应该有谱系、记忆和荣誉感。 1. 什么是「家族治理」？ FROST 引入了生物学的隐喻： Agent 家族 。 细胞会死，但谱系会存续。 Agent 会消亡，但宪法会传承。 资产会永存。 在这个框架里，有三个关键角色： 祖辈（Elder） ：定义不可违背的规则，是系统的「宪法」 父辈（Parent） ：负责领域协调，可以递归委托子任务 孙辈（Child） ：执行具体任务，用完即散 这不是简单的角色扮演，而是一套 结构化的治理协议 ： 协议一：层级 Store 继承 祖先 Store 对后代是只读的。后代只能继承和扩展，不能篡改祖先的记忆。 # 祖辈定义的宪法 ancestor_store = Store () ancestor_store . save ( " constitution " , { " rule_1 " : " always_validate_before_act " , " rule_2 " : " never_expose_raw_context " }) # 子孙只能继承，不能修改宪法 child_store = ChildStore ( ancestor_store ) 协议二：SOP 宪法校验 每个 SOP（标准操作流程）在执行前，必须经过祖辈审核。 # 子孙编写的 SOP child_sop = [ " fetch_user_data " , " process_payment " , " send_confirmation " ] # 执行前必须经过宪法校验 if not elder . validate_sop ( child_sop ): raise PermissionError ( " SOP violates constitution " ) 协议三：编排层级限制 禁止越级 spawn。父辈只能调度子辈，不能跨代指挥。 class Elder : max_spawn_generation = 0 # 祖辈不能 spawn class Parent : max_spawn_generation = 1 # 只能 spawn 子辈 class Child : max_spawn_generation = 2 # 只能 spawn 孙辈 协议四：选择性持久化 只有经过父辈审核的产出，才能进入家族记忆库。 # 子孙的临时产出 temp_result = child . execute ( task ) # 父辈决定是否收割 if parent . approve ( temp_result ): parent . merge_from ( child ) # 吸收有价值的结果 2. 为什么 Agent 需要「记忆传承」？ 当前大多数 Agent 框架的痛点： 每个对话都是全新的开始 。 你问 ChatGPT 一道数学题，它不会记得你上周问过类似的题目。你用 AutoGPT 做项目，它不会继承你之前调试的经验。 FROST 的解决方案是 分层的记忆系统 ： 层级 生命周期 用途 瞬时记忆 单次任务 工作区，只读不存 世代记忆 代际传递 子辈可继承祖先数据 宪法记忆 永久 不可修改，家族共享 经验记忆 按需收割 父辈选择性地吸收有价值产出 class HierarchicalStore ( Store ): """ 层级记忆系统 """ def __init__ ( self , ancestor_store = None ): self . ancestor = ancestor_store # 只读祖先记忆 self . local = {} # 本地可写记忆 def save ( self , key , value ): if key in self . ancestor : raise ValueError ( " Cannot override ancestor memory " ) self . local [ key ] = value def load ( self , key ): if key in self . local : return self . local [ key ] if key in self . ancesto