Wienerdog – memory and self-improving skills for Claude Code/Codex
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…
What it does
In the maker’s words, at launch
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 :)
Does the same job
all alternatives →
Huzzah – a novel approach to coding with AI17d ago · danielvaughn.dev · ▲384Hello everyone. I've been working on this experimental editor called Huzzah. I've been working almost exclusively with coding agents since January of this year, and over the past few months I began to feel utterly exhausted by them. They're great, but I'm finding it more and more tedious to write full sentences for every change I want. Not only that, but it seems there's a complexity limit for codebases - beyond a certain point the agent begins confusing itself. I'd like to go back to writing code, but I don't want to go all the way back to fully manual coding. So I've come up with this…
whoburnedmoreJun 2026 · whoburnedmore.com · ▲91Spotify Wrapped for Claude, Codex & a Public leaderboard.
- MAMulti-Agent-Coder Is #12 on Stanford's TBench. Beats Claude Code2025 · github.com · ▲5
This weekend I built a multi-agent coding system which, quite unexpectedly, beat Claude Code on Stanford's Terminal Bench! The architecture is straightforward, consisting of an orchestrator agent that deploys explorer & coder subagents to complete complex terminal based tasks, utilising an intelligent context sharing mechanism along the way which makes it all work. The repo has a lot of technical details, and all the code and prompts for you to play around with if you'd like! I had a lot of fun making this, I hope you have fun reading the README, using it yourself, or even extending it! As…
- IBI built simple and efficient local memory system for Claude CodeFeb 2026 · github.com · ▲6
I wanted to share a project I have been working on over the past week. It is a simple local memory system that saves your sessions into Markdown files, which can be viewed later. I developed this after using Claude Mem. I really enjoyed working with it, but it was consuming a lot of RAM, and each Claude session was becoming a major resource hog. I also tried other plugins and MCP solutions, but ran into similar issues, either slow performance or concerns about data being sent elsewhere. Because privacy was a big thing for me, I decided to build my own solution that keeps all data local.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com