Glavin Wiechert Glavin001

PRD.md - Product Requirements & Feature Inventory

Everything built on top of the base OpenClaw platform. Canonical reference for what exists, where it lives, and how it works. Operational use cases and workflow playbooks live in docs/USE-CASES-WORKFLOWS.md.

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

If you're using a high-end bluetooth headset on your Macbook Pro it's likely your mac is using an audio codec which favors battery efficiency over high quality. This results in a drastic degradation of sound, the SBC codec is the likely culprit, read more about it here.

Find out what codec you're using

Play a song on your headphones
Option (⌥) click the Bluetooth button at the top of your screen
If you're using AAC or aptX, you can stop here—those are the highest quality codecs.

Change your codec to AAC or aptX

	# OpenClaw Implementation Prompts

	Each prompt below is a self-contained brief you can hand to an AI coding assistant (or use as a project spec) to build that use case from scratch. Adapt the specific services to whatever you already use — the patterns are what matter.

	---

	## 1) Personal CRM Intelligence

	```
	Build me a personal CRM system that automatically tracks everyone I interact with, with smart filtering so it only adds real people — not newsletters, bots, or cold outreach.


	if (new URLSearchParams(window.location.search).get('portal')) {
	// <create start portal>
	// Create portal group to contain all portal elements
	const startPortalGroup = new THREE.Group();
	startPortalGroup.position.set(SPAWN_POINT_X, SPAWN_POINT_Y, SPAWN_POINT_Z);
	startPortalGroup.rotation.x = 0.35;
	startPortalGroup.rotation.y = 0;

	// Create portal effect

	import tqdm
	import numpy as np
	import torch
	import torch.distributed as dist
	import transformers

	def extract_xml_answer(text: str) -> str:
	answer = text.split("<final_answer>")[-1]
	answer = answer.split("</final_answer>")[0]
	return answer.strip()

	base_model: tiiuae/falcon-7b
	base_model_config: tiiuae/falcon-7b
	trust_remote_code: true
	model_type: AutoModelForCausalLM
	tokenizer_type: AutoTokenizer
	load_in_8bit: false
	load_in_4bit: true
	gptq: false
	strict: false
	push_dataset_to_hub:

	from langchain.llms.base import LLM
	from typing import Optional, List, Mapping, Any
	import requests
	from langchain.llms.utils import enforce_stop_tokens

	class CustomLLM(LLM):

	def __init__(self, url: str):
	self.url = url

	import { GeomUtils, TLCursor } from '@tldraw/core'
	import * as React from 'react'

	function getCursorCss(svg: string, r: number, f = false) {
	return (
	`url("data:image/svg+xml,<svg height='32' width='32' viewBox='0 0 35 35' xmlns='http://www.w3.org/2000/svg'><g fill='none' style='transform-origin:center center' transform='rotate(${r})${
	f ? ` scale(-1,-1) translate(0, -32)` : ''
	}'>` +
	svg.replaceAll(`"`, `'`) +
	'</g></svg>") 16 16, pointer'

	import getPixels from "get-pixels";
	import { max, min } from "lodash";
	import { NdArray } from "ndarray";
	import { Vector3 } from "three";

	// Example, use like:
	const makeHeightfieldColliderFromImage = async () => {
	const heightMapTexture = "myimage.png";
	const xSubdivisions = 200;
	const zSubdivisions = 200;