Documentation
The guides for people who use Monsters. They are read from the repository when the site is built, so they are always the ones in the code.
- ARCHITECTURE.md
Architecture
How Monsters is built: one local core, the event log, the kill switch, the orchestrator and its agents, the providers, the tools and the Markdown vault.Read the guide → - security-model.md
Security model
The perimeter, the threat model and the risks Monsters accepts: the local core, permissions, the action log, the kill switch and what the terminal permission really means.Read the guide → - subscriptions.md
Subscriptions
How to use the ChatGPT, Codex and Claude subscriptions you already pay for, and what Monsters does and does not do with them.Read the guide → - mcp-vault.md
The vault as an MCP server
Serve your Monsters notes to Claude Desktop, Codex, Cursor or Claude Code with `monsters mcp`: configuration, permissions and search.Read the guide → - remote.md
Remote use: SSH and Telegram
Use Monsters from another computer or from your phone: the terminal chat over SSH, the desktop app as an SSH client, and Telegram bots.Read the guide → - ROADMAP.md
Roadmap
Where Monsters has been and where it is going: finished phases, what is open before a stable release, and what comes later.Read the guide →
Also in the repository
- Technical decisions: Every non-obvious choice, with context and rationale. Mostly in Italian.
- Signing and updates: Packaging, signing and the signed update feed.
- Contributing: How to send a change, and the sign-off every commit needs.
These pages are generated from the Markdown files in the docs folder of the repository. To fix a mistake or add to a guide, open a pull request. docs on GitHub