thClaws
← home

thClaws User Manual

28 chapters · ภาษาไทย

A native-Rust AI agent workspace with CLI and desktop GUI. This manual covers everything from installation through building and deploying real projects — coding, automation, knowledge bases, and multi-agent teams.

Part I — Using thClaws

# Chapter
1 What is thClaws?
2 Installation
3 Desktop GUI tour
4 Working directory & running modes
5 Permissions
6 Providers, models & API keys
7 Sessions
8 Memory & project instructions (CLAUDE.md / AGENTS.md)
9 Knowledge bases (KMS)
10 Slash commands
11 Built-in tools
12 Skills
13 Hooks
14 MCP servers
15 Subagents
16 Plugins
17 Agent teams
19 Scheduling
20 Background research (/research)
21 LINE chat & web browser bridge
22 Paperclip adapter
23 Telegram bot
24 Facebook Page Messenger bot
25 Workflows (/workflow run)
26 GUI Shells
27 thClaws.cloud (catalog + hosted + gateway)

Part II — Case studies (chapters 28–30) — applied walkthroughs for building real projects with thClaws (static sites, Node.js apps, AI agents, deploying to Agentic Press) are in active development and will be added to this manual as each is reviewed and ready.

Appendices

# Appendix
A Providers, models & prices (thClaws.cloud gateway)

Conventions used in this manual

  • ❯ is the REPL prompt; what follows on that line is what you type.
  • $ is a shell prompt outside thClaws.
  • [tool: Bash: …] / [tokens: Xin/Yout · Ts] lines show what thClaws prints back.
  • Code fences without a language are terminal output; fences with a language (rust, json, bash) are files you write or commands you run.
  • Bold inside a command label indicates a required input (e.g. name).
  • Every chapter is self-contained — skip around freely.