AI Todo — 像很多程序员一样，我日常要兼顾工作任务、生活琐事、项目计划，时常感到事情多但漏掉的也不少。想用智能方式管理这些待办，但市面上的工具要么设计臃肿，要么 AI 能力很弱。于是我花了几周开发了 AI Todo，目标是:

dudemanAtl · HN

PlanWright – A control plane for AI coding agents

@EICWOGUP · X

Hey James, I am building that helps parents focus on their kids long term goals. Parents don’t have to be fluent on any skills to teach kids. All they have to do is choose the goal like chess, swimming, trachtenberg math, yoga etc and you get weekly list.

mistakevin · HN

I've been working on https://notebooker.ai if anyone is interested in giving some feedback. I tried to post a Show HN yesterday with details about how I built it, but was auto-flagged and not sure what rules I broke. Everything that I've built on top of open-notebook, like the plugin system for your own "creators" (aka, podcasts, infographics, etc) is at https://github.com/Notebooker-ai plus a Cloudflare Worker AI deployer to play with different models. Been working on it for about six months.

lerongwan1 · V2EX

上班前的三小时，属于我的独立开发时间 - - # 上班前的三小时，属于我的独立开发时间 白天要上班，真正能留给自己的整块时间并不多。 所以我开始在早上 5 点多起床。城市还没完全醒来，我已经坐到电脑前，用上班前的三个小时做自己的产品。 这段时间很安静，没有临时消息，也没有其他事情打断。每天只推进一点，可能只完成一个很小的任务，但它确实属于我。 早起并不轻松。不过一天最清醒的时间，正在被我用来完成真正想做的事。 我的产品，怎么才能有用户 -> [使用 NoteDeep 开始整理你的知识库]( https://www.notedeep.com) #独立开发 #副业 #程序员日常 #个人产品 #NoteDeep

@chickencoopsai · X

Building the chickenverse and it’s awesome. Say hello to prez Clump. Join us now

@trackowork · X

@Hanumliahzhra · X

vibecoding free tier Just discovered Vibe Coding Plan - AI-powered project planning that breaks down ideas into actionable tasks! Check it out

@TimEngng · X

Stop losing the "why" behind product decisions -

@AadyaAI · X

Aadya AI turns a client conversation into a branded, ready-to-send proposal or invoice PDF in 60 seconds — no templates, no formatting, no chasing.

@harryjwang · X

I've used many of the major conference systems. Plenty still have docs as an unsearchable static site — or worse, as PDFs that stopped tracking the product three versions ago. Somehow, still true in 2026. We took an AI-first path with instead. Our docs are generated from the codebase itself. A custom Claude Code skill writes each page and retakes the screenshots whenever a feature changes — so the docs don't drift from the product. Every page still gets reviewed by a human before it ships. Now you can talk to them, too. We just shipped "Ask AI" over our docs: This feature also turned out to be a nice teaching case for agentic RAG vs. classic RAG: • Classic RAG: chunk → embed → vector DB → retrieve once, by fixed rules • Agentic RAG: hand the model a search tool and let it drive — write a query, read the results, rewrite, retry At more than 100 pages, still no vector database needed. And every answer cites the exact page it came from. #Age