@latent_node · X

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:

@discorev · X

I've been working on - Using gpt-5.6-sol and Fable in Claude Code via CLIProxyAPI. I've found using these two together with Claude Code Workflows is a killer combination

@oaZsxer · X

Cheers mate. Built this.

@propelio_app · X

Hey man, Building Propelio, proposals for freelancers Let’s connect!

dudemanAtl · HN

PlanWright – A control plane for AI coding agents

@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

douvy · HN

Educational tool for understanding AI agents. Code: https://github.com/douvy/how-agents-think

@yaseenvalji · X

built this in a couple hours with Claude Code on Fable 5 ultracode. any hard decision goes to a board of 5 AI advisors: they debate live, a Chair calls it, and it remembers the outcome. open source, on the Claude API. @AnthropicAI

@helloukey · X

@AjayGB4 · X

@abhishekbariyaa · X