Handbooks

One page per tool: what it is, when to use it, setup, deployment, daily use, pitfalls, and every tutorial about it.

H

Hermes Agent

A free, open-source AI agent from Nous Research that learns from its own work: it writes reusable skills, remembers you, and runs on Mac, Windows and Linux.

6 chapters

O

OpenClaw

A free, open-source AI assistant that runs on your own computer and answers you in the chat apps you already use, such as Telegram, WhatsApp, Slack and Discord.

6 chapters

O

Obsidian

A free note app that keeps every note as a plain Markdown file on your own computer. A good home for a personal knowledge base that AI agents can read and write.

6 chapters

S

Strata

A free, open-source app that runs very large AI models on an ordinary gaming PC, with no account and no cloud, and plugs into coding agents like Claude Code.

6 chapters

P

Polymarket

A prediction market: people trade on the outcome of real events, and the price of a "Yes" share reads as the crowd's probability that it happens.

6 chapters

C

Cloudflare

The company that sits between your website and its visitors: domains, DNS, HTTPS and protection for free, plus Workers and D1 to run a whole site without renting a server.

7 chapters

X

Xiaozhi AI

An open-source AI voice assistant you build on a cheap ESP32 board: talk to it like a smart speaker, and choose which AI model answers.

6 chapters

E

ESP32

A cheap, tiny chip with Wi-Fi and Bluetooth built in: the brain inside countless smart-home gadgets, sensors and DIY AI voice assistants.

6 chapters

H

Home Assistant

Free, open-source software that runs your smart home from your own computer: lights, sensors, plugs and cameras in one place, with no cloud account required.

7 chapters

C

Cache

A cache keeps a copy of work already done so the next request is faster and cheaper. For AI, the big one is prompt caching.

6 chapters

P

PromptPick

A prompt is everything you send to the model: how to write one that gets the answer you wanted the first time.

6 chapters

W

Workflow

A workflow is a fixed chain of steps that runs on its own, with an AI model doing the thinking inside some of them.

6 chapters

S

SkillPick

A skill is a folder of instructions an AI agent loads when a task matches: how to write one, and how to make it reliable.

6 chapters

L

LLMPick

The large language model is the "brain" inside every AI assistant and agent: what it is, what it can do and where it fails.

6 chapters

C

Context

Everything the model can see while it answers: your instructions, the conversation so far, attached files and tool results. It has a hard size limit.

6 chapters

M

Memory

What an AI assistant keeps from one conversation to the next, and how to control it.

6 chapters

K

Knowledge BasePick

Your documents, organized so an AI can look things up in them and answer with the facts you wrote, not with guesses.

6 chapters

M

Muse AI

A video hosting platform that indexes what is said and shown in your videos, so people can search inside them.

6 chapters

G

GitHub

Where code lives and changes are reviewed. Also the place most AI coding agents deliver their work, as pull requests.

6 chapters

C

ClaudePick

Anthropic's family of AI models and the apps built on them: the Claude chat app, Claude Code for terminal work, and the API.

6 chapters

C

Codex

OpenAI's coding agent: give it a task in your repository and it writes, runs and tests the code, locally or in the cloud.

6 chapters

A

API

The way programs talk to a service. For AI, it means sending text to a model over the internet and getting text back.

6 chapters

M

MCPPick

Model Context Protocol: a standard plug that lets an AI assistant use your tools and data without custom integration work.

6 chapters

T

Token

The unit AI models read, write and charge by. Roughly a short word in English, about one or two characters in Chinese.

6 chapters