A reference document for working with the opmlProjectEditor format used by Dave Winer's OPML Editor and Frontier-based tools.
opmlProjectEditor is a way of storing a multi-file software project in a single OPML file. Each top-level outline node under the project headline represents a file. The file's contents are stored as child outline nodes, one node per line, with indentation representing code structure.
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:
| from typing import Generator | |
| class SequenceValidator: | |
| def __init__(self) -> None: | |
| self._generator = self.check() | |
| self._consumed = -1 | |
| next(self._generator) | |
| def feed(self, text: str) -> tuple[int, bool | None]: |
| import dspy | |
| from dspy.evaluate import Evaluate | |
| from dspy.teleprompt import * | |
| import csv | |
| # Load the emails | |
| with open('training.csv', 'r') as file: | |
| reader = csv.DictReader(file) | |
| emails = [row for row in reader] |
| #!/bin/bash | |
| # | |
| # gpush: Lazy git add, commit, and push with comments written by LLM | |
| # | |
| # | |
| # This script provides an enhanced git push workflow with the following features: | |
| # - Automatically pulls latest changes from the current branch | |
| # - Checks for uncommitted changes | |
| # - Generates commit messages using AI (LLM/Gemini) if no message is provided | |
| # - Allows interactive editing of auto-generated commit messages |
| import argparse | |
| import random | |
| import sys | |
| from transformers import AutoModelForCausalLM, AutoTokenizer, DynamicCache | |
| import torch | |
| parser = argparse.ArgumentParser() | |
| parser.add_argument("question", type=str) | |
| parser.add_argument( |
human (Oct 30, 2024, 06:03 PM)
I want to ask the analysis stage llm (a very advanced multimodal LLM) to assess I want to ask the LLM to assess is the snippet politically left-leaning or right-leaning (on a spectrum of -1.0 to +1.0 where -1.0 is extremely left-leaning and +1.0 is extremely right leaning). Please help me to add this to the prompt. Here is the existing prompt that I want you to add it to:
| #!/usr/bin/env bash | |
| # | |
| # A Bash script to run a TDD loop for building a Python module to pass tests. | |
| set -euo pipefail | |
| # How many times to loop. | |
| ATTEMPTS=4 | |
| # The system prompt to use when creating the initial version. |
| #!/bin/bash | |
| if [ -z "$1" ]; then | |
| echo "Usage: $0 <input_video>" | |
| exit 1 | |
| fi | |
| input_file="$1" | |
| if [ -z "$2" ]; then |
