小女仆机器人: Self-hosted Messaging Agent

Understand the project

Practical overview

When it fits

Use it when you can operate a self-hosted service and want an assistant that combines conversation with memory, reminders, retrieval and proactive messaging in supported channels.

Who it is for

Operators who want to host an AI assistant within QQ or another supported messaging entry point.
Individuals or communities that need conversations alongside reminders, RSS delivery or local knowledge retrieval.
Developers who want to inspect or adapt an MIT-licensed Rust agent.

Documented uses

Hold multi-turn conversations through a messaging channel.
Keep managed long-term conversational memory and retrieve information from a local knowledge base.
Track todos and reminders, and deliver RSS updates.
Use web queries, multimodal input and tool calling in assistant interactions.
Run documented local commands for divination or tabletop initiative and hidden-roll workflows.

Before you choose

Requirements & limits

The project is open source under the MIT license. The README documents Linux and Windows release installers, Docker Compose deployment and source builds. Source builds require Rust; the Linux installer does not. The documented Windows release is x86_64 only.

At least one messaging entry point and a usable model provider must be configured before running the bot.
The official QQ entry requires a QQ Open Platform AppID and AppSecret; OneBot 11 and an optional WeChat service-account text entry are also described.
Docker deployment is available for operators who already use containers; the run image does not include Rust or Node.js.
The Web Console manages the deployed bot and its configuration; it is not a separate chatbot service.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the release on Linux and configure the bot

Set up the Linux release, configure a messaging entry point and model provider, then start the service.

Before you start

A Linux host.
At least one messaging entry point and a usable model provider.
For the official QQ entry, a QQ Open Platform AppID and AppSecret.

Steps

Download the installer and run its deploy command: the command below followed by the command below.
Documented command
```
curl -fsSL https://github.com/kuliantnt/qq-maid-bot/raw/refs/heads/master/scripts/qbot.sh -o /tmp/qbot.sh
```
Documented command
```
bash /tmp/qbot.sh deploy
```
Run qbot install and choose whether to enable the Web Console.
Configure the messaging bot and AI provider with qbot config bot and qbot config ai.
Start the service with qbot start and check its status with qbot status.

Expected outcome

The release is installed, configured for a messaging entry point and model provider, and started as a service.

Guide limitations

The guide covers Linux release installation, not configuration details for each messaging platform or model provider.
The installer downloads the latest release; the README describes SHA-256 verification for downloaded packages.

Documentation 1 ↗

Evidence and transparency

Sources & review

Official repository ↗

Source record details

Source availability: Active
Sources checked: 12 October 2026
Original website title: kuliantnt/qq-maid-bot · Official homepage title · retained in its source language

How we review sources Suggest a correction

小女仆机器人