30 docs tagged with "Guide"

This guide connects nanoinfra to Discord so a Discord user or server channel can

Connect nanoinfra to Matrix, on matrix.org or on a homeserver you run.

This guide connects nanoinfra to Mattermost through the built-in Mattermost

Connect nanoinfra to Microsoft Teams through an Azure Bot registration.

Connect nanoinfra to Signal through the signal-cli daemon, so the agent answers on a

This guide connects nanoinfra to Slack through Socket Mode. No public webhook URL

This guide connects nanoinfra to WhatsApp through the whatsapp channel. The

This guide turns nanoinfra into an email AI agent that polls IMAP for accepted

Use this guide to add a self-contained channel package to the nanoinfra repository. A channel is part of nanoinfra when its package lives at nanoinfra/channels//. There is no separate external channel-plugin path.

This guide connects one Telegram bot to nanoinfra. Messages sent to that bot use

Use this page after nanoinfra agent -m "Hello!" works locally. Deployment keeps long-running surfaces online: WebUI, chat apps, heartbeat, Dream, cron jobs, and channel connections.

This page collects contributor-facing notes for extending nanoinfra. User-facing setup and runtime options live in configuration.md.

A guide is a walkthrough: one outcome, shortest path, followed start to finish. A reference

This guide explains how to use nanoinfra's long-term AI agent memory: session

nanoinfra can call OpenAI-compatible model providers by configuring an apiBase,

nanoinfra can trace supported OpenAI-compatible provider calls through Langfuse's

This guide adds an MCP server to nanoinfra so the agent can use external tools

Model fallback lets nanoinfra try a primary model first, then fall back to one or

nanoinfra includes built-in web search and web fetch tools. Search uses

nanoinfra can run as a self-hosted chatbot or AI agent in Telegram, Discord,

The nanoinfra gateway is the long-running self-hosted AI agent process. It keeps WebUI sessions,

Some Ollama model templates move or remove tool definitions as a conversation

By default nanoinfra authenticates a token, not a person. Two operators who share that token are

nanoinfra can keep agent work alive across turns through sustained goals,

nanoinfra can expose a local OpenAI-compatible endpoint behind

This guide covers the practical controls to review before letting a nanoinfra

nanoinfra includes a browser WebUI for persistent chat sessions, visible agent

Run multiple nanoinfra instances simultaneously with separate configs and runtime data. Use --config as the main entrypoint. Optionally pass --workspace during onboard when you want to initialize or update the saved workspace for a specific instance.

This guide shows when to use the nanoinfra Python SDK instead of calling a model

This page is for cases where you already know what you want to connect and need a pasteable setup. Each recipe shows what to set, what to run, and what a failure usually means.