| editor.addKeyMap({ | |
| // bold | |
| 'Ctrl-B': function(cm) { | |
| var s = cm.getSelection(), | |
| t = s.slice(0, 2) === '**' && s.slice(-2) === '**'; | |
| cm.replaceSelection(t ? s.slice(2, -2) : '**' + s + '**', 'around'); | |
| }, | |
| // italic | |
| 'Ctrl-I': function(cm) { | |
| var s = cm.getSelection(), |
| """ | |
| The most atomic way to train and run inference for a GPT in pure, dependency-free Python. | |
| This file is the complete algorithm. | |
| Everything else is just efficiency. | |
| @karpathy | |
| """ | |
| import os # os.path.exists | |
| import math # math.log, math.exp |
See more of my writing here.
In this post, I'll start from scratch and build up to OpenClaw's architecture step by step, showing how you could have invented it yourself from first principles, using nothing but a messaging API, an LLM, and the desire to make AI actually useful outside the chat window.
End goal: understand how persistent AI assistants work, so you can build your own (or become an OpenClaw power user).
When you use ChatGPT or Claude in a browser, there are several limitations:
Companion prompts for the video: OpenClaw after 50 days: 20 real workflows (honest review)
These are the actual prompts I use for each use case shown in the video. Copy-paste them into your agent and adjust for your setup. Most will work as-is or the agent will ask you clarifying questions.
Each prompt describes the intent clearly enough that the agent can figure out the implementation details. You don't need to hand-hold it through every step.
My setup: OpenClaw running on a VPS, Discord as primary interface (separate channels per workflow), Obsidian for notes (markdown-first), Coolify for self-hosted services.
Install the midisport-firmware package (firmware is in the package and the package should be available via the debian package repository)
sudo apt-get install midisport-firmware
sudo touch /etc/udev/rules.d/99-midisport-firmware.rules
sudo vi /etc/udev/rules.d/99-midisport-firmware.rules
In the editor, paste the following rules:
| KFZUS-F3JGV-T95Y7-BXGAS-5NHHP | |
| T3ZWQ-P2738-3FJWS-YE7HT-6NA3K | |
| KFZUS-F3JGV-T95Y7-BXGAS-5NHHP | |
| 65Z2L-P36BY-YWJYC-TMJZL-YDZ2S | |
| SFZHH-2Y246-Z483L-EU92B-LNYUA | |
| GSZVS-5W4WA-T9F2E-L3XUX-68473 | |
| FTZ8A-R3CP8-AVHYW-KKRMQ-SYDLS | |
| Q3ZWN-QWLZG-32G22-SCJXZ-9B5S4 | |
| DAZPH-G39D3-R4QY7-9PVAY-VQ6BU | |
| KLZ5G-X37YY-65ZYN-EUSV7-WPPBS |
Note
This does not works in browser for quests which require you to play a game! Use the desktop app to complete those.
How to use this script:
Console tab
| ... | |
| func faviconHandler(w http.ResponseWriter, r *http.Request) { | |
| http.ServeFile(w, r, "relative/path/to/favicon.ico") | |
| } | |
| ... | |
| func main() { | |
| http.HandleFunc("/favicon.ico", faviconHandler) | |
| } |
| { | |
| "input": { | |
| "blocklist": [], | |
| "compressor#0": { | |
| "attack": 15.0, | |
| "boost-amount": 0.0, | |
| "boost-threshold": -72.0, | |
| "bypass": false, | |
| "dry": -80.01, | |
| "hpf-frequency": 10.0, |