Hacker News

Show HN: DSCode – Coding Agent Powered by DeepSeek

Hacker News - Sat, 08/01/2026 - 11:07am

Plan, edit, test, and review code from your terminal. Local sessions, sandboxed tools, and readable token costs.

Comments URL: https://news.ycombinator.com/item?id=49135106

Points: 1

# Comments: 0

Categories: Hacker News

Single-file Ada 83 LLVM compiler

Hacker News - Sat, 08/01/2026 - 11:07am
Categories: Hacker News

Show HN: Wienerdog – memory and self-improving skills for Claude Code/Codex

Hacker News - Sat, 08/01/2026 - 9:44am

The idea of Wienerdog was born out of my experience setting up my own simple but effective system of memory, self-improving skills and hooks for Claude Code and Codex. As I was teaching my friends and colleagues how to set up their own I found myself automating more and more of my system setup and finally I decided to publish it on GitHub to help others get more out of their AI usage.

So what is Wienerdog? Simply put, it is just files — no daemon, no server, no telemetry: a collection of instructions and skills that you can install by pasting just one line (npx wienerdog@latest init) and it will give your Claude Code / Codex:

- a proper base information CLAUDE.md / AGENTS.md file created by doing a simple, friendly interview with you (existing files are respected — Wienerdog only writes inside its own clearly-marked block). - a persistent, markdown-based memory vault following the PARA convention, similar to the Obsidian vaults many folks use. Already have a vault? No problem, you can just point it to it. - automated ‘hooks’ that will pull in key information (who you are, what you do, etc.) into each session and detect and save critical new information into your persistent memory. - automated daily ‘dreaming’ runs that digest the previous day’s sessions and store their key information into memory. If your computer is off or asleep at that time, the dreaming run will catch up when you're back. - repeating task patterns are identified and turned into reusable skills which can be further improved automatically. - if you are using both Claude Code and Codex (like I do) they will be able to read from and contribute to the same memory vault. You are not locked in to any vendor. - a basic (and optional) integration with the Google suite to give your AI access to your Gmail, Calendar and Drive — read-only and draft-only by default.

Everything Wienerdog does can run on your existing Anthropic / OpenAI subscription, in line with their terms. The project is open-source on GitHub and free forever under the MIT license. I do this for fun and to give a little something back.

I have put quite a bit of work into Wienerdog already and am happily using it myself for its own development (dogfooding — get it?). In fact, most of Wienerdog's code was written by AI agents following its own spec system, using the memory vault that lives in the repo. With that said, it is still early and a work in progress that could use more eyes. I'd love for you to try it out and ask questions, request new things to add or even contribute on GitHub if you have the time and capacity.

P.S. Why the name Wienerdog? Because I love these little tube-shaped snouty sausage clowns :)

Comments URL: https://news.ycombinator.com/item?id=49134381

Points: 1

# Comments: 0

Categories: Hacker News

Libration

Hacker News - Sat, 08/01/2026 - 9:42am
Categories: Hacker News

How the smartest people use AI

Hacker News - Sat, 08/01/2026 - 9:37am
Categories: Hacker News

Show HN: Reimagine place photos with Nano Banana

Hacker News - Sat, 08/01/2026 - 9:33am

Article URL: https://aigoogleearth.app/

Comments URL: https://news.ycombinator.com/item?id=49134295

Points: 1

# Comments: 0

Categories: Hacker News

Wyro – Draw a backend on a canvas, export TypeScript with no lock-in

Hacker News - Sat, 08/01/2026 - 9:32am

Hi HN. Wyro is a visual backend builder that compiles to a plain TypeScript repo you own outright.

The motivation: AI app builders got good at generating apps and stayed bad at letting you leave. Frontend code you can always lift out. The backend is the hostage — their runtime, their DB, their deploy target.

How it works: you wire blocks on a canvas (HTTP routes, tables, auth, queues, cron, multi-step pipelines) into a graph. That graph is an IR, and the compiler lowers it to a conventional Node project — typed Express handlers, Drizzle schema and migrations, Zod validators derived from the table definitions, `postgres` for the driver. Nothing is interpreted at runtime; the graph isn't shipped, it's compiled away.

The test I hold it to: the exported package.json lists express, drizzle-orm, postgres, zod, dotenv, jsonwebtoken. No package of mine. Delete your Wyro account and the app keeps running.

Databases work the same way — connect your own Supabase and provisioning happens in your org, on your bill, over the Management API. I hold the canvas, not your infrastructure.

Honest state of things: it's early and solo-built. The generated code is the thing I'm most confident about and the thing I most want torn apart. Rough edges are in the surrounding product, not the compiler.

Free tier, no card. The useful thing you can do in five minutes is export a project and read the diff-able code before deciding whether you trust it.

https://wyro.vercel.app

Would especially like feedback from anyone who has migrated off a hosted builder — what broke, and what you wished the export had included.

Comments URL: https://news.ycombinator.com/item?id=49134292

Points: 1

# Comments: 0

Categories: Hacker News

Pages