| """ | |
| 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:
| #!/usr/bin/env python3 | |
| # mini-openclaw.py - A minimal OpenClaw clone | |
| # Run: uv run --with anthropic --with schedule python mini-openclaw.py | |
| import anthropic | |
| import subprocess | |
| import json | |
| import os | |
| import re | |
| import threading |
This protocol governs how two agents collaborate on engineering tasks with a built-in adversarial review process. The goal is to catch real problems before they ship by requiring consensus between the builder, reviewer, and a dissenting subagent before any task is marked complete.
| name | description |
|---|---|
orchestrating-swarms |
Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns. |
Master multi-agent orchestration using Claude Code's TeammateTool and Task system.
| import { EventEmitter } from "events"; | |
| import { nanoid } from "nanoid"; | |
| interface ChatCompletionChunk { | |
| id: string; | |
| object: "chat.completion.chunk"; | |
| created: number; | |
| model: string; | |
| choices: Array<{ | |
| index: number; |
| 'system': | |
| [ | |
| { | |
| 'type': 'text', | |
| 'text': "You are Claude Code, Anthropic's official CLI for Claude.", | |
| 'cache_control': {'type': 'ephemeral'} | |
| }, | |
| { | |
| 'type': 'text', | |
| 'text': 'You are an interactive CLI tool that helps users with software engineering tasks. |
| #!/bin/bash | |
| export WANDB_API_KEY=<your key> | |
| export WANDB_PROJECT=<org/project> | |
| litellm --port 4000 --debug --config cc-proxy.yaml |
Here's a simple way for Claude Code users to switch from the costly Claude models to the newly released SOTA open-source/weights coding model, Qwen3-Coder, via OpenRouter using LiteLLM on your local machine.
This process is quite universal and can be easily adapted to suit your needs. Feel free to explore other models (including local ones) as well as different providers and coding agents.
I'm sharing what works for me. This gu
| # /// script | |
| # requires-python = ">=3.12" | |
| # dependencies = [ | |
| # "click", | |
| # "mistralai", | |
| # "markdown", | |
| # "requests", | |
| # "beautifulsoup4", | |
| # ] | |
| # /// |