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:
| for k,v in sorted(foo.items()): | |
| print k, v | |
| for k in sorted(foo.keys()): | |
| print k, foo[k] | |
| More at: https://stackoverflow.com/questions/364519/in-python-how-do-i-iterate-over-a-dictionary-in-sorted-key-order |
| import json | |
| with open('json_file.json') as f: | |
| data = json.load(f) | |
| print(data) |
| """ | |
| y2k | |
| 19016 -> 01/23/2020 | |
| 0 = 12/31/1967 | |
| 1 = 01/01/1968 | |
| """ | |
| import sys | |
| from datetime import datetime, timedelta |
| curl https://raw.githubusercontent.com/sivel/speedtest-cli/master/speedtest.py | python - | |
| # Silent version | |
| #curl -s https://raw.githubusercontent.com/sivel/speedtest-cli/master/speedtest.py | python - |
| p 15count_coverage.py 2>&1 | tee out.txt |
| nme = ["aparna", "pankaj", "sudhir", "Geeku"] | |
| deg = ["MBA", "BCA", "M.Tech", "MBA"] | |
| scr = [90, 40, 80, 98] | |
| # New from dictionary | |
| dict = {'name': nme, 'degree': deg, 'score': scr} | |
| df = pd.DataFrame(dict) | |
| clean_df.to_csv(OUTPUT_FILENAME, index=False) | |
| # New dataframe from subset of pandas dataframe |
| # Histogram of words per document in the first page | |
| import matplotlib.pyplot as plt | |
| plt.style.use("ggplot") | |
| plt.hist([s for s in words_per_doc], bins=10) | |
| plt.xlabel('Documents') | |
| plt.ylabel('Number of words') | |
| plt.show() |
| df = pd.read_csv(FILENAME, names=["id", "title", "text"], | |
| escapechar='\\', encoding='utf-8', header=0) | |
| print(df.describe()) # Summary statistics (count, unique, top, freq) for every column of the dataframe | |
| print(df.info()) # Information about each column on the dataframe, and memory usage | |
| print(df.head()) # Show first 5 rows of dataframe | |
| print(df.head(3)) # Show first 3 rows of dataframe | |
| # Head with only a few columns, with random sampling of 10 rows |