惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

D
DataBreaches.Net
IT之家
IT之家
博客园_首页
博客园 - 【当耐特】
V
V2EX
Apple Machine Learning Research
Apple Machine Learning Research
G
Google Developers Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Recent Announcements
Recent Announcements
F
Fortinet All Blogs
GbyAI
GbyAI
腾讯CDC
H
Hackread – Cybersecurity News, Data Breaches, AI and More
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
I
InfoQ
H
Help Net Security
T
Tailwind CSS Blog
B
Blog RSS Feed
Martin Fowler
Martin Fowler
人人都是产品经理
人人都是产品经理
The Cloudflare Blog
博客园 - 叶小钗
雷峰网
雷峰网
量子位

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
Show HN: I built a local-first Web-to-EPUB tool after Omn...
nick_jonas · 2026-05-05 · via Hacker News: Show HN

Site: [https://any2ebook.com](https://any2ebook.com)

I have two young sons, and honestly, only when their "batteries" are fully drained for the day does the remaining time truly belong to me. That's when I finally get to spend time reading online—blogs, long-form articles, and newsletters.

I relied on Omnivore to handle this. I have to say it was a great tool, but one day they suddenly announced they were shutting down the service, leaving us with very little time to migrate. That was the first time I truly felt like I was being kicked out. I spent so much time collecting content I loved, but in the end, it was stored in someone else’s repository—it felt as though those things never really belonged to me.

After that, I tried several alternatives like EpubPress, dotepub, etc. They were okay, but they all had limitations—like conversion limits, service interruptions, or being too complicated to use (they had way too many input fields; some parameters I didn’t even understand hahah... I just wanted to click a button and get it done). More importantly, my data was dependent on someone else’s servers.

It consists of two main parts: a browser extension that captures open tabs or bookmarks, and a desktop app that converts them into clean, readable EPUBs. The two communicate via a local HTTP port. The entire conversion process happens right on your machine—no data ever leaves your computer.

You use it, you own it.

One more thing,

I also work with a lot of academic papers, so I added a PDF to EPUB feature. It uses AI to handle complex math typesetting and OCR. It really put me through the mill. I would certainly prefer to handle PDF OCR locally as well, but current local models are not yet mature enough. Running a powerful OCR model requires a high-performance PC, making it difficult for me to strike a balance between recognition accuracy and hardware requirements. Therefore, it is currently implemented using well-known, high-quality LLMs such as Mistral and DeepSeek, so it is a paid feature.

I wrote the full story behind the project here: https://any2ebook.com/story

I'd love to hear your thoughts on the local-first approach!