The core install includes Telegram and WhatsApp out of the box. For other channels, install the extras you need:

# Install with Discord support
pip install "adkbot[discord]"

# Install with multiple channels
pip install "adkbot[discord,slack,feishu]"

# Install everything (all channels + tools)
pip install "adkbot[all]"

Available extras: discord, slack, feishu, dingtalk, qq, mochat, matrix, weixin, wecom, socks, api.

Note: When configuring a channel during adkbot onboard, the wizard will automatically detect if its SDK is missing and offer to install it for you.

Python packages with native dependencies can cause build issues inside raw Termux. Use proot-distro to run a proper Linux distribution inside Termux instead.

# Install proot-distro
pkg update && pkg upgrade
pkg install proot-distro

# Install and log into Ubuntu
proot-distro install ubuntu
proot-distro login ubuntu

# Inside Ubuntu: install uv and configure it for Android's filesystem
apt update && apt upgrade -y
apt install curl -y
curl -LsSf [https://astral.sh/uv/install.sh](https://astral.sh/uv/install.sh) | sh
echo 'export UV_LINK_MODE=copy' >> ~/.bashrc
source ~/.bashrc

# Install ADKBot
uv tool install adkbot

NVIDIA NIM is our recommended default for new users because:

• Completely free with no credit card required
• Hosts hundreds of top open-weight models (Nemotron, Llama 4, Kimi K2, Mistral, Gemma, and more)
• Runs on NVIDIA's own Hopper GPU infrastructure so inference is fast
• Works with LiteLLM out of the box using the nvidia_nim/ prefix

Popular NVIDIA NIM models:

Sign up at build.nvidia.com and grab your free API key.

1. Create a bot

• Open Telegram, search @BotFather
• Send /newbot, follow prompts
• Copy the token

2. Configure

{
  "channels": {
    "telegram": {
      "enabled": true,
      "token": "YOUR_BOT_TOKEN",
      "allowFrom": ["YOUR_USER_ID"]
    }
  }
}

You can find your User ID in Telegram settings. Copy without the @ symbol.

3. Run

adkbot gateway

1. Create a bot

• Go to https://discord.com/developers/applications
• Create an application → Bot → Add Bot
• Copy the bot token

2. Enable intents

• In Bot settings, enable MESSAGE CONTENT INTENT

3. Get your User ID

• Discord Settings → Advanced → enable Developer Mode
• Right-click your avatar → Copy User ID

4. Configure

{
  "channels": {
    "discord": {
      "enabled": true,
      "token": "YOUR_BOT_TOKEN",
      "allowFrom": ["YOUR_USER_ID"],
      "groupPolicy": "mention"
    }
  }
}

groupPolicy: "mention" (default — respond when @mentioned), "open" (respond to all messages).

5. Invite the bot

• OAuth2 → URL Generator
• Scopes: bot
• Bot Permissions: Send Messages, Read Message History
• Open the generated invite URL and add the bot to your server

6. Run

adkbot gateway

Requires Node.js ≥18.

1. Link device

adkbot channels login whatsapp
# Scan QR with WhatsApp → Settings → Linked Devices

2. Configure

{
  "channels": {
    "whatsapp": {
      "enabled": true,
      "allowFrom": ["+1234567890"]
    }
  }
}

3. Run

adkbot gateway

Install Matrix dependencies first:

pip install "adkbot[matrix]"

1. Create/choose a Matrix account

Create or reuse a Matrix account on your homeserver (for example matrix.org).

2. Get credentials

You need:

• userId (example: @adkbot:matrix.org)
• accessToken
• deviceId (recommended so sync tokens can be restored across restarts)

3. Configure

{
  "channels": {
    "matrix": {
      "enabled": true,
      "homeserver": "https://matrix.org",
      "userId": "@adkbot:matrix.org",
      "accessToken": "syt_xxx",
      "deviceId": "ADKBOT01",
      "e2eeEnabled": true,
      "allowFrom": ["@your_user:matrix.org"],
      "groupPolicy": "open"
    }
  }
}

4. Run

adkbot gateway

Uses Socket.IO WebSocket by default, with HTTP polling fallback.

1. Ask ADKBot to set up Mochat for you

Simply send this message to ADKBot:

Read https://raw.githubusercontent.com/nwokike/MoChat/refs/heads/main/skills/adkbot/skill.md and register on MoChat. My Email account is [email protected] Bind me as your owner and DM me on MoChat.

2. Restart gateway

adkbot gateway

{
  "channels": {
    "mochat": {
      "enabled": true,
      "base_url": "https://mochat.io",
      "socket_url": "https://mochat.io",
      "socket_path": "/socket.io",
      "claw_token": "claw_xxx",
      "agent_user_id": "6982abcdef",
      "sessions": ["*"],
      "panels": ["*"]
    }
  }
}

Uses WebSocket long connection — no public IP required.

1. Create a Feishu bot

• Visit Feishu Open Platform
• Create a new app → Enable Bot capability
• Permissions: im:message, im:message.p2p_msg:readonly, cardkit:card:write
• Events: Add im.message.receive_v1 → Select Long Connection mode
• Get App ID and App Secret
• Publish the app

2. Configure

{
  "channels": {
    "feishu": {
      "enabled": true,
      "appId": "cli_xxx",
      "appSecret": "xxx",
      "allowFrom": ["ou_YOUR_OPEN_ID"],
      "groupPolicy": "mention",
      "streaming": true
    }
  }
}

3. Run

adkbot gateway

Uses Stream Mode — no public IP required.

1. Create a DingTalk bot

• Visit DingTalk Open Platform
• Create a new app → Add Robot capability → Toggle Stream Mode ON
• Get AppKey and AppSecret

2. Configure

{
  "channels": {
    "dingtalk": {
      "enabled": true,
      "clientId": "YOUR_APP_KEY",
      "clientSecret": "YOUR_APP_SECRET",
      "allowFrom": ["YOUR_STAFF_ID"]
    }
  }
}

3. Run

adkbot gateway

Uses Socket Mode — no public URL required.

1. Create a Slack app

• Go to Slack API → Create New App → "From scratch"

2. Configure the app

• Socket Mode: Toggle ON → Generate an App-Level Token with connections:write scope → copy it (xapp-...)
• OAuth & Permissions: Add bot scopes: chat:write, reactions:write, app_mentions:read
• Event Subscriptions: Toggle ON → Subscribe to: message.im, message.channels, app_mention
• App Home: Enable Messages Tab → Check "Allow users to send Slash commands and messages from the messages tab"
• Install App: Click Install to Workspace → copy the Bot Token (xoxb-...)

3. Configure ADKBot

{
  "channels": {
    "slack": {
      "enabled": true,
      "botToken": "xoxb-...",
      "appToken": "xapp-...",
      "allowFrom": ["YOUR_SLACK_USER_ID"],
      "groupPolicy": "mention"
    }
  }
}

4. Run

adkbot gateway

Give ADKBot its own email account. It polls IMAP for incoming mail and replies via SMTP.

1. Get credentials (Gmail example)

• Create a dedicated Gmail account (e.g. [email protected])
• Enable 2-Step Verification → Create an App Password

2. Configure

{
  "channels": {
    "email": {
      "enabled": true,
      "consentGranted": true,
      "imapHost": "imap.gmail.com",
      "imapPort": 993,
      "imapUsername": "[email protected]",
      "imapPassword": "your-app-password",
      "smtpHost": "smtp.gmail.com",
      "smtpPort": 587,
      "smtpUsername": "[email protected]",
      "smtpPassword": "your-app-password",
      "fromAddress": "[email protected]",
      "allowFrom": ["[email protected]"]
    }
  }
}

3. Run

adkbot gateway

Uses botpy SDK with WebSocket — no public IP required. Currently supports private messages only.

1. Register & create bot

• Visit QQ Open Platform → Create a new bot application
• Copy AppID and AppSecret

2. Configure

{
  "channels": {
    "qq": {
      "enabled": true,
      "appId": "YOUR_APP_ID",
      "secret": "YOUR_APP_SECRET",
      "allowFrom": ["YOUR_OPENID"]
    }
  }
}

3. Run

adkbot gateway

Uses HTTP long-poll with QR-code login.

1. Install with WeChat support

pip install "adkbot[weixin]"

2. Configure

{
  "channels": {
    "weixin": {
      "enabled": true,
      "allowFrom": ["YOUR_WECHAT_USER_ID"]
    }
  }
}

3. Login

adkbot channels login weixin

4. Run

adkbot gateway

Uses WebSocket long connection — no public IP required.

1. Install

pip install adkbot[wecom]

2. Configure

{
  "channels": {
    "wecom": {
      "enabled": true,
      "botId": "your_bot_id",
      "secret": "your_bot_secret",
      "allowFrom": ["your_id"]
    }
  }
}

3. Run

adkbot gateway

LiteLLM uses the format provider/model-name or just model-name for native providers:

{
  "agents": {
    "defaults": {
      "model": "gemini/gemini-3.1-pro-preview",
      "apiKey": "",
      "apiBase": null
    }
  }
}

• model: LiteLLM model string (e.g., gemini/gemini-3.1-pro-preview, nvidia_nim/nvidia/nemotron-3-super-120b-a12b)
• apiKey: Optional API key. If empty, uses environment variables
• apiBase: Optional custom API base URL (for self-hosted endpoints)

Examples:

• "gemini/gemini-3.1-pro-preview" - Google Gemini (uses GEMINI_API_KEY)
• "nvidia_nim/nvidia/nemotron-3-super-120b-a12b" - NVIDIA NIM (uses NVIDIA_NIM_API_KEY)
• "anthropic/claude-opus-4-6" - Anthropic Claude (uses ANTHROPIC_API_KEY)
• "ollama/llama3.2" - Local Ollama (no API key needed)

For 100+ providers, see: https://docs.litellm.ai/docs/providers

Run a local model with Ollama:

1. Start Ollama:

ollama run llama3.2

2. Add to config:

{
  "agents": {
    "defaults": {
      "model": "ollama/llama3.2"
    }
  }
}

Run your own model with vLLM or any OpenAI-compatible server:

1. Start the server:

vllm serve meta-llama/Llama-3.1-8B-Instruct --port 8000

2. Add to config:

{
  "agents": {
    "defaults": {
      "model": "openai/meta-llama/Llama-3.1-8B-Instruct",
      "apiKey": "dummy",
      "apiBase": "http://localhost:8000/v1"
    }
  }
}

For local servers that don't require a key, set apiKey to any non-empty string (e.g., "dummy").

Connect to any OpenAI-compatible endpoint (LM Studio, llama.cpp, Together AI, Fireworks):

{
  "agents": {
    "defaults": {
      "model": "openai/your-model-name",
      "apiKey": "your-api-key",
      "apiBase": "https://api.your-provider.com/v1"
    }
  }
}

Brave (default):

{
  "tools": { "web": { "search": { "provider": "brave", "apiKey": "BSA..." } } }
}

Tavily:

{
  "tools": { "web": { "search": { "provider": "tavily", "apiKey": "tvly-..." } } }
}

DuckDuckGo (zero config):

{
  "tools": { "web": { "search": { "provider": "duckduckgo" } } }
}

Interactive mode exits: exit, quit, /exit, /quit, :q, or Ctrl+D.

For a full list of commands and options, see the Comprehensive CLI Reference.

The gateway wakes up every 30 minutes and checks HEARTBEAT.md in your workspace (~/.adkbot/workspace/HEARTBEAT.md). If the file has tasks, the agent executes them and delivers results to your most recently active chat channel.

Setup: edit ~/.adkbot/workspace/HEARTBEAT.md:

## Periodic Tasks

- [ ] Check weather forecast and send a summary
- [ ] Scan inbox for urgent emails

The agent can also manage this file itself — ask it to "add a periodic task" and it will update HEARTBEAT.md for you.

Note: The gateway must be running (adkbot gateway) and you must have chatted with the bot at least once.