LibreFang
中文

Enterprise Channels

Enterprise collaboration platform integrations.

Microsoft Teams

Prerequisites

  • A Microsoft Azure account with access to the Azure Bot Service
  • A registered Azure AD application with a client ID and secret

Setup

  1. Go to the Azure Portal and create a new Bot Channels Registration (or Azure Bot resource).
  2. Under Configuration, note the Microsoft App ID.
  3. Go to Certificates & secrets and create a new client secret. Copy it immediately.
  4. In the Teams Admin Center, enable your bot for the organization or upload a custom app manifest.
  5. Set environment variables:
export TEAMS_APP_ID=your-azure-app-id         # Environment variable
export TEAMS_APP_SECRET=your-azure-client-secret
librefang vault set TEAMS_APP_ID              # Encrypted vault (recommended)
librefang vault set TEAMS_APP_SECRET
librefang config set-key teams                # .env file
# Or set via dashboard "Set API Key" button   # secrets.env
  1. Add to config:
[channels.teams]
app_id_env = "TEAMS_APP_ID"
app_secret_env = "TEAMS_APP_SECRET"
default_agent = "ops"
  1. Configure the messaging endpoint in Azure to point to your LibreFang instance's public URL (e.g., https://your-domain.com:4545/channels/teams/webhook).
  2. Restart the daemon.

How It Works

The Teams adapter uses the Microsoft Bot Framework v3 webhook protocol with OAuth2 token exchange. Incoming messages arrive via HTTPS POST to the shared API server at /channels/teams/webhook, and the adapter authenticates each request by validating the JWT bearer token against Azure AD. Responses are sent back through the Bot Framework REST API.

Mattermost

Prerequisites

  • A Mattermost server (self-hosted or cloud) with admin access
  • A bot account or personal access token

Setup

  1. In Mattermost, go to Integrations > Bot Accounts and create a new bot, or go to Account Settings > Security > Personal Access Tokens and generate a token.
  2. Copy the token.
  3. Set environment variables:
export MATTERMOST_TOKEN=your-bot-token        # Environment variable
export MATTERMOST_URL=https://mattermost.example.com
librefang vault set MATTERMOST_TOKEN          # Encrypted vault (recommended)
librefang vault set MATTERMOST_URL
librefang config set-key mattermost           # .env file
# Or set via dashboard "Set API Key" button   # secrets.env
  1. Add to config:
[channels.mattermost]
token_env = "MATTERMOST_TOKEN"
url_env = "MATTERMOST_URL"
default_agent = "ops"
  1. Restart the daemon.

How It Works

The Mattermost adapter connects to the Mattermost server via WebSocket for real-time event delivery and uses the REST v4 API for sending messages. It listens for new post events and routes them to the configured agent.

Google Chat

Prerequisites

  • A Google Cloud project with the Google Chat API enabled
  • A service account key file (JSON)

Setup

  1. In the Google Cloud Console, enable the Google Chat API.
  2. Create a service account and download the JSON key file.
  3. Configure a Chat app in the Google Chat API settings, selecting the HTTP endpoint connection type. Set the endpoint URL to your LibreFang instance (e.g., https://your-domain.com:4545/channels/google_chat/webhook).
  4. Set environment variables:
export GOOGLE_CHAT_SA_KEY=/path/to/sa-key.json  # Environment variable
export GOOGLE_CHAT_SPACE=spaces/AAAA_BBBBBB
librefang vault set GOOGLE_CHAT_SA_KEY        # Encrypted vault (recommended)
librefang vault set GOOGLE_CHAT_SPACE
librefang config set-key google_chat          # .env file
# Or set via dashboard "Set API Key" button   # secrets.env
  1. Add to config:
[channels.google_chat]
sa_key_env = "GOOGLE_CHAT_SA_KEY"
space_env = "GOOGLE_CHAT_SPACE"
default_agent = "ops"
  1. Restart the daemon.

How It Works

The Google Chat adapter authenticates using a service account and receives messages via webhook callbacks on the shared API server at /channels/google_chat/webhook. Responses are sent back through the Google Chat REST API using the space and thread identifiers from the incoming message.

Webex

Prerequisites

Setup

  1. Go to developer.webex.com and sign in.
  2. Navigate to My Webex Apps and create a new Bot.
  3. Copy the bot access token.
  4. Set the environment variable:
export WEBEX_BOT_TOKEN=your-webex-bot-token   # Environment variable
librefang vault set WEBEX_BOT_TOKEN           # Encrypted vault (recommended)
librefang config set-key webex                # .env file
# Or set via dashboard "Set API Key" button   # secrets.env
  1. Add to config:
[channels.webex]
token_env = "WEBEX_BOT_TOKEN"
default_agent = "assistant"
  1. Restart the daemon.

How It Works

The Webex adapter registers a webhook with the Webex API to receive message events. Incoming messages are fetched via the Webex REST API using the message ID from the webhook payload, and responses are posted back through the messages endpoint.

Feishu / Lark

Prerequisites

Setup

  1. Go to the Feishu Open Platform and create a custom application.
  2. Enable Bot under the app's capabilities.
  3. Note the App ID and App Secret from the app credentials page.
  4. Configure event subscriptions to point to your LibreFang instance's webhook URL (e.g., https://your-domain.com:4545/channels/feishu/webhook).
  5. Set environment variables:
export FEISHU_APP_ID=your-app-id              # Environment variable
export FEISHU_APP_SECRET=your-app-secret
librefang vault set FEISHU_APP_ID             # Encrypted vault (recommended)
librefang vault set FEISHU_APP_SECRET
librefang config set-key feishu               # .env file
# Or set via dashboard "Set API Key" button   # secrets.env
  1. Add to config:
[channels.feishu]
app_id_env = "FEISHU_APP_ID"
app_secret_env = "FEISHU_APP_SECRET"
default_agent = "assistant"
  1. Restart the daemon.

How It Works

The Feishu adapter receives message events via webhook callbacks on the shared API server at /channels/feishu/webhook. It obtains a tenant access token using the app credentials, then uses the Feishu REST API to send message replies. Event payloads are verified using the app's verification token.

Processing-State Reactions

Feishu shows live "I'm working on it" feedback by adding a Typing reaction to the user's message on receive and removing it once the reply is sent. Both calls are fire-and-forget — API failures warn! but never block message processing. See Reactions and Processing State on the channels overview.

@Mention Preservation

The Feishu adapter substitutes each @_user_N placeholder with @<display-name> resolved from the mention payload (falling back to open_id when name is absent), and rewrites @_all to @all. Agents see the original conversational text — "@alice can you check this?" — instead of bare punctuation. See Feishu @Mention Preservation.

Rocket.Chat

Prerequisites

  • A Rocket.Chat server with admin access (from Rocket.Chat)
  • A bot user account or personal access token

Setup

  1. In Rocket.Chat, go to Administration > Rooms or create a bot user.
  2. Generate a personal access token via My Account > Personal Access Tokens.
  3. Set environment variables:
export ROCKETCHAT_TOKEN=your-access-token     # Environment variable
export ROCKETCHAT_URL=https://chat.example.com
librefang vault set ROCKETCHAT_TOKEN          # Encrypted vault (recommended)
librefang vault set ROCKETCHAT_URL
librefang config set-key rocketchat           # .env file
# Or set via dashboard "Set API Key" button   # secrets.env
  1. Add to config:
[channels.rocketchat]
token_env = "ROCKETCHAT_TOKEN"
url_env = "ROCKETCHAT_URL"
default_agent = "assistant"
  1. Restart the daemon.

How It Works

The Rocket.Chat adapter polls the Rocket.Chat REST API for new messages at a regular interval. Incoming messages are routed to the configured agent, and responses are posted back through the REST API's chat endpoints.

Zulip

Prerequisites

  • A Zulip server account (cloud or self-hosted)
  • A bot created in Settings > Your bots (see Zulip API docs)

Setup

  1. In Zulip, go to Settings > Your bots and click Add a new bot.
  2. Choose Generic bot and create it.
  3. Note the bot's email address and API key.
  4. Set environment variables:
export ZULIP_EMAIL=bot@example.zulipchat.com  # Environment variable
export ZULIP_API_KEY=your-api-key
export ZULIP_URL=https://example.zulipchat.com
librefang vault set ZULIP_EMAIL               # Encrypted vault (recommended)
librefang vault set ZULIP_API_KEY
librefang vault set ZULIP_URL
librefang config set-key zulip                # .env file
# Or set via dashboard "Set API Key" button   # secrets.env
  1. Add to config:
[channels.zulip]
email_env = "ZULIP_EMAIL"
api_key_env = "ZULIP_API_KEY"
url_env = "ZULIP_URL"
default_agent = "assistant"
  1. Restart the daemon.

How It Works

The Zulip adapter uses Zulip's event queue API for long-polling. It registers an event queue for message events, then continuously polls the queue for new messages. Responses are sent via the messages REST endpoint.

Flock

Prerequisites

Setup

  1. Go to docs.flock.com and create a new bot.
  2. Copy the bot token.
  3. Set the environment variable:
export FLOCK_BOT_TOKEN=your-flock-bot-token   # Environment variable
librefang vault set FLOCK_BOT_TOKEN           # Encrypted vault (recommended)
librefang config set-key flock                # .env file
# Or set via dashboard "Set API Key" button   # secrets.env
  1. Add to config:
[channels.flock]
token_env = "FLOCK_BOT_TOKEN"
default_agent = "assistant"
  1. Restart the daemon.

How It Works

The Flock adapter receives messages via webhook callbacks on the shared API server at /channels/flock/webhook. Responses are sent back through the Flock REST API's chat.sendMessage endpoint.

Twist

Prerequisites

Setup

  1. Go to developer.twist.com and create a new integration.
  2. Copy the integration token.
  3. Set the environment variable:
export TWIST_TOKEN=your-twist-token           # Environment variable
librefang vault set TWIST_TOKEN               # Encrypted vault (recommended)
librefang config set-key twist                # .env file
# Or set via dashboard "Set API Key" button   # secrets.env
  1. Add to config:
[channels.twist]
token_env = "TWIST_TOKEN"
default_agent = "assistant"
  1. Restart the daemon.

How It Works

The Twist adapter polls the Twist REST API v3 for new messages in configured channels and threads. Responses are posted back via the API's comment or message endpoints.

Pumble

Prerequisites

  • A Pumble workspace with bot integration support (see Pumble Help)

Setup

  1. In Pumble, configure a bot integration for your workspace.
  2. Copy the bot token.
  3. Set the environment variable:
export PUMBLE_BOT_TOKEN=your-pumble-bot-token # Environment variable
librefang vault set PUMBLE_BOT_TOKEN          # Encrypted vault (recommended)
librefang config set-key pumble               # .env file
# Or set via dashboard "Set API Key" button   # secrets.env
  1. Add to config:
[channels.pumble]
token_env = "PUMBLE_BOT_TOKEN"
default_agent = "assistant"
  1. Restart the daemon.

How It Works

The Pumble adapter receives messages via webhook callbacks on the shared API server at /channels/pumble/webhook. Responses are sent back through the Pumble API.

Guilded

Prerequisites

Setup

  1. Go to your Guilded server settings and create a bot.
  2. Copy the bot token.
  3. Set the environment variable:
export GUILDED_BOT_TOKEN=your-guilded-token   # Environment variable
librefang vault set GUILDED_BOT_TOKEN         # Encrypted vault (recommended)
librefang config set-key guilded              # .env file
# Or set via dashboard "Set API Key" button   # secrets.env
  1. Add to config:
[channels.guilded]
token_env = "GUILDED_BOT_TOKEN"
default_agent = "assistant"
  1. Restart the daemon.

How It Works

The Guilded adapter connects to the Guilded API via WebSocket for real-time message events. Responses are sent through the Guilded REST API's channel message endpoints.