dabit3

PI is a TypeScript toolkit for building AI agents. It's a monorepo of packages that layer on top of each other: pi-ai handles LLM communication across providers, pi-agent-core adds the agent loop with tool calling, pi-coding-agent gives you a full coding agent with built-in tools, session persistence, and extensibility, and pi-tui provides a terminal UI for building CLI interfaces.

These are the same packages that power OpenClaw. This guide walks through each layer, progressively building up to a fully featured coding assistant with a terminal UI, session persistence, and custom tools.

By understanding how to compose these layers, you can build production-grade agentic software on your own terms, without being locked into a specific abstraction.

Pi was created by @badlogicgames. This is a great writeup from him that explains some of the design decisions made when creating it.

The stack

dabit3

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).

First, let's establish the problem

When you use ChatGPT or Claude in a browser, there are several limitations:

dabit3

#!/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

dabit3

OpenClaw on DigitalOcean

1. Create a Droplet

Ubuntu 24.04 LTS, nearest region

2. Select Premium AMD

2 GB RAM / 1 AMD CPU / 50 GB NVMe

3. SSH into server

dabit3

import Anthropic from "@anthropic-ai/sdk";
import { Pool } from "pg";

const anthropic = new Anthropic();

// dn connection - Claude never sees this
const db = new Pool({
  host: "your-database-host.com",
  port: 5432,
  database: "sales_db",

dabit3

You Could've Invented Claude Code

This is cross-posted from the original x post.

What makes Claude Code powerful is surprisingly simple: it's a loop that lets an AI read files, run commands, and iterate until a task is done.

The complexity comes from handling edge cases, building a good UX, and integrating with real development workflows.

In this post, I'll start from scratch and build up to Claude Code's architecture step by step, showing how you could have invented it yourself from first principles, using nothing but a terminal, an LLM API, and the desire to make AI actually useful.

dabit3

Building AI agents with the Claude Agent SDK

If you've used Claude Code, you've seen what an AI agent can actually do—read files, run commands, edit code, figure out the steps to accomplish a task.

And you know it doesn't just help you write code, it takes ownership of problems and works through them the way a thoughtful engineer would.

The Claude Agent SDK is the same engine, yours to point at whatever problem you want, so you can easily build agents of your own.

The Claude Agent SDK is how you build that same thing into your own applications.

dabit3

Create an OpenAI inference component based on the ETH Price Oracle (components/eth-price-oracle). The component should:

1. Accept input in the format 'PROMPT|OPENAI_API_KEY|SEED' from a Makefile parameter
2. Use fetch_json and http_request_post_json for API communication
3. Return and log only choices[0].message.content and choices[0].finish_reason
4. Include proper input validation and SEED should be an integer
5. Use the main makefile, do not create a separate one.

Important Implementation Details:

dabit3

I want to create a similar oracle to the ETH Price Oracle at components/eth-price-oracle, but I want it to use the SportRadar API.

I want to set and reference the SportRadar API key from the Makefile, I do not want to use an .env file..

The request parameters for calling the SportRadar API look like this:

curl --request GET \
     --url 'https://api.sportradar.com/ncaamb/trial/v8/en/games/fa15684d-0966-46e7-a3f8-f1d378692109/boxscore.json?api_key={insert-api-key} \
     --header 'accept: application/json'

dabit3

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { z } from "zod";
import 'dotenv/config'

const server = new McpServer({
  name: "EigenLayer AVS service",
  version: "1.0.0",
});