Generated by Code IQ · v1.0

picoclaw
Knowledge Tutorial

PicoClaw is an ultra-lightweight personal AI agent designed to run on embedded devices and development boards. It acts as a central "brain" that connects various communication channels (like Telegram or Discord) to Large Language Models (LLMs) to understand and process user requests. Uniquely, it combines long-term memory with a modular skills system, allowing the AI to interact directly with the physical world through hardware interfaces (GPIO, I2C, SPI) and local system tools.

7
Chapters
-
Subsystems
∞
Rabbit Holes
▶ Start Reading ⎇ View on GitHub
System Architecture

How the pieces fit

picoclaw is organized as connected concepts and components. Start broad, then drill down chapter by chapter.

⚙️
Communication Channels
Communication Channels
👥
The Agent Loop
The Agent Loop
⚙️
LLM Providers
LLM Providers
⚙️
Context & Memory Builder
Context & Memory Builder
⚙️
Skills System
Skills System
🔧
Tool Registry & Execution
Tool Registry & Execution
⚙️
Hardware Interface
Hardware Interface
picoclaw — bash
➜open tutorial
◆ Scanning numbered chapters
◆ Building navigation and Mermaid diagrams
◆ Generating chapter and subsystem pages
✓ 7 chapter pages built
✓ Theme toggle enabled
➜
Repository Overview

Intro and Architecture Diagram

PicoClaw is an ultra-lightweight personal AI agent designed to run on embedded devices and development boards. It acts as a central "brain" that connects various communication channels (like Telegram or Discord) to Large Language Models (LLMs) to understand and process user requests. Uniquely, it combines long-term memory with a modular skills system, allowing the AI to interact directly with the physical world through hardware interfaces (GPIO, I2C, SPI) and local system tools.

Source Repository: https://github.com/sipeed/picoclaw

flowchart TD A0["The Agent Loop"] A1["Tool Registry & Execution"] A2["Communication Channels"] A3["Context & Memory Builder"] A4["Skills System"] A5["LLM Providers"] A6["Hardware Interface"] A2 -->|"Dispatches user input"| A0 A0 -->|"Constructs session context"| A3 A3 -->|"Ingests training manuals"| A4 A0 -->|"Queries for intelligence"| A5 A0 -->|"Invokes capabilities"| A1 A1 -->|"Controls physical devices"| A6 A0 -->|"Sends replies"| A2
Tutorial Chapters

All 7 chapters

Follow sequentially or jump to any topic. Start with Communication Channels.

Ch.01 CORE
Communication Channels
Welcome to the world of PicoClaw! Before we can build a brain for our AI agent, we need to give it a way to interact with the outside world.
↗
Ch.02 AGENTS
The Agent Loop
In the previous chapter, Communication Channels, we gave our agent "ears" to hear messages and a "mouth" to speak. But right now, if a user…
↗
Ch.03 CORE
LLM Providers
In the previous chapter, The Agent Loop, we built the "Conductor" of our application—the loop that manages the cycle of Thinking, Acting, a…
↗
Ch.04 CORE
Context & Memory Builder
In the previous chapter, LLM Providers, we connected our agent to a powerful "Brain" (like GPT-4 or Claude).
↗
Ch.05 CORE
Skills System
In the previous chapter, Context & Memory Builder, we gave our agent a personality and the ability to remember previous conversations.
↗
Ch.06 TOOLS
Tool Registry & Execution
Welcome back! In the previous chapter, Skills System, we taught our agent how to use tools by giving it instruction manuals (Markdown files…
↗
Ch.07 CORE
Hardware Interface
Welcome to the final chapter of the PicoClaw tutorial!
↗
About This Project

Generated by Code IQ

This tutorial was automatically generated by Code IQ and rendered with the shared tutorial site builder. It can be produced for any repository tutorial folder that follows the numbered markdown chapter layout.

View Code IQ ↗
python build_site.py '/home/runner/work/Code-IQ/Code-IQ/output/picoclaw'

// → 7 chapters
// → source: sipeed/picoclaw