/agent-teams

name: agent-teams
description: Interact with Microsoft Teams - send messages, read channels, manage reactions
version: 2.38.0
allowed-tools: Bash(agent-teams:*)
metadata:
  openclaw:
    requires:
      bins:
        - agent-teams
    install:
      - kind: node
        package: agent-messenger
        bins: [agent-teams]

Agent Teams

A TypeScript CLI tool that enables AI agents and humans to interact with Microsoft Teams through a simple command interface. Features seamless token extraction from the Teams desktop app (with browser fallback) and multi-team support.

Quick Start

# Get team snapshot (credentials are extracted automatically)
agent-teams snapshot

# Send a message
agent-teams message send <team-id> <channel-id> "Hello from AI agent!"

# List channels
agent-teams channel list <team-id>

Authentication

Two co-equal ways to sign in — pick whichever fits:

1. **`agent-teams auth login`** (work/school **or** personal Microsoft accounts) — device-code sign-in. Open the printed URL, enter the code, and approve in your browser. No desktop app or browser extraction needed. It prompts for your Microsoft email (or pass `--email <email>`) and auto-detects work vs personal, then starts the matching flow; pass `--account-type work|personal` to force it and skip detection. Only `auth login` stores the AAD refresh token required by `message search`. 2. **`agent-teams auth extract`** — zero-config extraction from the Teams desktop app, falling back to a Chromium browser. Best when you're already signed into Teams locally. Yields a Skype token only — sufficient for messaging, but **not** for `message search` (see below).

Credentials are also extracted automatically on first use of any command if none are stored, so `auth extract` can happen silently in the background.

Teams tokens are short-lived (60-90 minutes for extraction, a few hours for device-code). **Device-code accounts (`auth login`) refresh silently** — the CLI re-mints an expired token from the stored refresh token with no re-login needed. Extraction accounts re-extract automatically as long as you're still signed into the Teams desktop app or a supported browser; if that fails, re-run `auth extract` (or switch to `auth login`).

Non-interactive `auth login` (agents / CI)

When there's no TTY, `auth login` splits into two calls:

# 1. Start — returns verification_uri, user_code, and device_code as JSON.
#    Pass --email to auto-detect the account type (no prompt without a TTY),
#    or --account-type work|personal to force it.
agent-teams auth login --email <email>

# 2. After the user approves in a browser, finish with the device_code
agent-teams auth login --device-code <device_code>

`--client-id <id>` overrides the AAD client ID on either call (or set `AGENT_TEAMS_CLIENT_ID`). `--account-type <work|personal>` selects the account (default `work`); it is preserved across the two-call flow, so pass it to both calls when signing in to a personal account non-interactively.

Multi-Team Support

# List all available teams
agent-teams team list

# Switch to a different team
agent-teams team switch <team-id>

# Show current team
agent-teams team current

# Check auth status (includes token expiry info)
agent-teams auth status

Multi-Account Support (Work / Personal)

# Switch between work and personal accounts
agent-teams auth switch-account work
agent-teams auth switch-account personal

# Use a specific account for one command (without switching)
agent-teams snapshot --account work

Memory

The agent maintains a `~/.config/agent-messenger/MEMORY.md` file as persistent memory across sessions. This is agent-managed — the CLI does not read or write this file. Use the `Read` and `Write` tools to manage your memory file.

Reading Memory

At the **start of every task**, read `~/.config/agent-messenger/MEMORY.md` using the `Read` tool to load any previously discovered team IDs, channel IDs, user IDs, and preferences.

• If the file doesn't exist yet, that's fine — proceed without it and create it when you first have useful information to store.
• If the file can't be read (permissions, missing directory), proceed without memory — don't error out.

Writing Memory

After discovering useful information, update `~/.config/agent-messenger/MEMORY.md` using the `Write` tool. Write triggers include:

• After discovering team IDs and names (from `team list`, `snapshot`, etc.)
• After discovering useful channel IDs and names (from `channel list`, `snapshot`, etc.)
• After discovering user IDs and names (from `user list`, `user me`, etc.)
• After the user gives you an alias or preference ("call this the standup channel", "my main team is X")
• After discovering channel structure (standard vs private channels)

When writing, include the **complete file content** — the `Write` tool overwrites the entire file.

What to Store

• Team IDs with names
• Channel IDs with names and team context
• User IDs with display names
• User-given aliases ("standup channel", "main team")
• Account preferences (work vs personal)
• Any user preference expressed during interaction

What NOT to Store

Never store tokens, credentials, or any sensitive data. Never store full message content (just IDs and channel context). Never store file upload contents.

Handling Stale Data

If a memorized ID returns an error (channel not found, team not found), remove it from `MEMORY.md`. Don't blindly trust memorized data — verify when something seems off. Prefer re-listing over using a memorized ID that might be stale.

Format / Example

# Agent Messenger Memory

## Teams

- `team-id-1` — Acme Corp (default, work account)
- `team-id-2` — Side Project (personal account)

## Channels (Acme Corp)

- `channel-id-1` — General
- `channel-id-2` — Engineering
- `channel-id-3` — Standups

## Users (Acme Corp)

- `user-id-1` — Alice (engineering lead)
- `user-id-2` — Bob (backend)