AQBot

📖 Overview

AQBot is a local-first open-source desktop AI workstation. It unifies multi-provider chat, ACP Agent, knowledge base, MCP tools, and a local API gateway while keeping data on your machine.

⚙️ Connect to BeeHears

BeeHears is a New API–compatible relay. In most apps, fill in the three fields below using a token from the BeeHears console:

📚 Setup guide

In the BeeHears console, go to System Settings -> Chat Settings and add the

following shortcut option. It lets users fill AQBot from the token

management page with one click:

AQBot is a local-first, open-source desktop AI workbench (AGPL-3.0). It

unifies multi-provider chat, ACP agents, knowledge bases, MCP tools, and a

local API gateway, while keeping app data and user files on the machine.

• Official Website: https://app.aqbot.top
• GitHub: https://github.com/AQBot-Desktop/AQBot
• Download: GitHub Releases
• Official Docs: Getting Started

Core Features

• Multi-provider chat — Connect OpenAI, Claude, Gemini, DeepSeek, Qwen, and any OpenAI-compatible endpoint
• Provider import — Import a provider from an aqbot:// link after confirmation
• Model management — Sync remote model lists, capability tags, and latency tests
• Agent — In-chat Agent (uses your configured provider APIs) plus an ACP Agent workbench
• Local data — App state lives in ~/.aqbot/; user files live in ~/Documents/aqbot/

See the AQBot website for the full feature set. This page covers BeeHears integration only.

BeeHears Integration Method

Please use your self-deployed BeeHears, or ensure that the service provider has a BeeHears service with legal upstream authorization and compliance obligations. Do not integrate API addresses or keys from unknown sources into a production environment.

Method 1: One-Click Import (Recommended)

1. Install AQBot and open it at least once so the system registers the aqbot:// protocol
2. In the BeeHears console, add the JSON above under System Settings → Chat Settings
3. Open Token Management and choose AQBot from the token actions
4. The browser launches AQBot. Confirm the provider name, API host, type openai, and key prefix
5. After confirmation, AQBot opens Settings → Provider Management. It reuses a provider with the same API host + type, or creates a new one
6. Open that provider, click Sync Models, then return to chat and select a model

{address} is the BeeHears site root (for example https://ai.beehears.com), with no query string. For the OpenAI type, AQBot appends /v1 automatically. Import does not validate the key or sync models.

Method 2: Manual Configuration

1. Copy the API Key from BeeHears Token Management
2. In AQBot, go to Settings → Provider Management → Add Provider
3. Fill in:

1. Click Sync Models to pull the models currently exposed by BeeHears
2. Return to chat and select a synced model

API Host Notes

• Prefer the site root and let AQBot append /v1
• If the host already ends with /v1, AQBot will not append another one
• Add a trailing ! only when you must disable automatic completion

Optional: Native Protocols

If BeeHears also exposes Claude or Gemini native APIs, add another provider:

Change type in the one-click template to anthropic or gemini. The same API key can back multiple providers.

FAQ

• Clicking AQBot does not open the app: Install and launch the desktop app first. Opening only the website or a Vite dev server does not register aqbot://
• Import succeeds but chat fails: Click Sync Models, and make sure the model ID matches the name BeeHears actually exposes
• macOS says the app is damaged or the developer cannot be verified: Follow the AQBot README and Getting Started to allow this app. You do not need to turn Gatekeeper off
• The one-click link contains an API key: Generate it only on the signed-in token page. Do not post URLs that embed a real key

Related Links

• AQBot GitHub
• Configure Providers (official docs)
• Download

🔗 Related links

• Back to docs
• BeeHears Console
• Official
• GitHub
• Upstream reference (New API docs)