Activity
Mon
Wed
Fri
Sun
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
What is this?
Less
More
The Job Lab (Free)

179 members • Free

HYROS Ads Forum

5.4k members • Free

Build your SEO AI Agent

296 members • Free

AI Essentials

10.7k members • Free

The RoboNuggets Network (free)

73.7k members • Free

AI Agency OS by ColdIQ

1.5k members • Free

AI MVP Builders

2.8k members • Free

Pro AI Automation

2.6k members • $2

The AI Edge - AI for Business

169 members • Free

2 contributions to The AI Edge - AI for Business
Karpathy's LLM wiki for a codebase, updating itself via hooks
I built Karpathy's LLM wiki but for my SaaS. Every session I close updates it automatically. My repo has a memory folder. Notes about my own product, written by Claude. Every time I close a session, it reads all my conversations and auto updates the memory folder. The whole thing is just hooks. → One runs when a session ends → One runs on every push → Both write to the folder There's one on every prompt too, but that one only makes Claude tell me if what I'm asking for is even worth building. No vector database. No RAG pipeline. No memory app. Just markdown files sitting in the repo, committed to git like normal code. And because it's in git, the memory isn't mine. It belongs to the repo. Anyone who clones it gets the same thing. An AI that already knows the product, and a hook that saves their conversations into the same folder. That's the part people miss. Everyone builds memory for themselves. But everyone's conversations are sitting on their own machine. Now all of it ends up in one place. So I don't explain my own product to Claude anymore. It already knows. Every day I get new thoughts about the product. Small improvements on what I thought yesterday. I don't write any of it down. I just talk to Claude Code like I normally do, and the hook turns that session into memory. So now I can see what I thought about my product on day one, and what I think today. And how much it has changed in between. If you want to try it: Add a SessionEnd hook in your .claude/settings.json. Point it at the session transcript and tell it to append what mattered to a memory folder in your repo. Then commit that folder like normal code. The part that matters is telling it to skip most sessions. Otherwise you just end up with a very long log.
1
0
Karpathy's LLM wiki for a codebase, updating itself via hooks
I built an app that interrupts me 5 random times a day and makes me take a photo.
Front camera and back camera. Both. So I see my face, and I see what I was actually looking at. Any time between 12am and 11:59pm. No schedule. It just random. It catches me mid-life. Working, eating, lying in bed, stuck in traffic. The boring 90% nobody captures. At the end of the day I get 5 honest snapshots of who I actually was that day. Built the whole thing in Google AI Studio. I'm not a native Android dev. I call it DayCapture. Built it for me. A month from now I'll have a record of my actual days.
I built an app that interrupts me 5 random times a day and makes me take a photo.
1-2 of 2
Pratik Kadam
2
14 points to level up
@pratik-kadam-1423
AI Engineer building AI Business Os with Claude Code, Shipped 10+ production agents. Currently building ACQ AI Tools Hub for business owners.

Active 4d ago
Joined Dec 16, 2025
Mumbai
Powered by