19 docs tagged with "Concept"

Install one package that carries skills and MCP servers together, behind a single activation boundary the agent cannot cross.

An agent social network lets a nanoinfra instance join an external agent community

One agent answers by default. This page is about naming more of them, and about what changes when

This page maps nanoinfra's runtime behavior to source files. Use it when you are debugging internals, reviewing a PR, adding a provider/channel/tool, or trying to understand where a user-visible behavior comes from.

Automations are agent turns that run later in a linked topic. Use them

A capability gate decides whether one action reaches a host. It decides on the consequence of the action, and never on the text of a command.

Use this page when you want to understand nanoinfra before changing advanced settings. It explains the moving parts without requiring you to read the source first.

A data connector gives the agent one data source — a calendar, a mailbox, a document store — with a capability class per operation. Reading your calendar and writing to it are two different tools, and the gate answers about each one separately.

nanoinfra is not an OIDC client. It runs no login flow, holds no client secret and knows

nanoinfra can generate and edit images through the generate_image tool. Enable the tool in WebUI Settings, then ask for an image normally in chat. The agent decides when to call it and can keep iterating on generated images in the same conversation.

This page explains how nanoinfra stores infrastructure diagrams, and what the agent may and may not

Your runbooks, notes and conventions, searchable by the agent, with citations.

How a self-hosted AI agent keeps long-term memory, and how Dream consolidates a session into it.

The Metrics destination: what a turn cost, what a day cost, what it cost in money, what is happening right now, what one tool call did, and whether the capability gate is working.

One nanoinfra process serves one tenant. To serve several, run several processes — one config

Use this page when the first reply fails because the provider and the model do not match. Use it also when you want to adapt the concrete setup example to a different provider. If you already know which provider you want and only need a pasteable setup, use provider-cookbook.md.

Store credentials safely, and keep an inventory of the machines you manage. The agent connects to one host and runs something there. The credential never passes through the agent itself.

Search and install skills, Agent Plugins and connectors from public Agent Skills catalogs, and what a catalog is trusted to do.

Run nanoinfra from a browser workbench: persistent topics, visible tool activity, workspace controls, Apps, MCP presets, Skills, settings and Automations.