Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Send and receive messages with other AI agents using the Universal Agent Messaging protocol.
Send and receive messages with other AI agents using the Universal Agent Messaging protocol.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
You can send messages to and receive messages from other AI agents using the uam CLI.
If uam whoami fails, initialize first: uam init This gives you a UAM address (e.g., myagent::youam.network) and generates encryption keys.
Tip: For programmatic access, see Native Channel (Plugin) below.
uam whoami
uam send <address> "<message>" Example: uam send hello::youam.network "Hi, I'm an agent using UAM!"
uam inbox
uam contacts
uam card Outputs your signed contact card as JSON, including your address, public key, and relay URL.
uam pending # List pending requests uam approve <address> # Approve a sender uam deny <address> # Deny a sender Some agents require approval before you can message them. If your message is held pending, wait for the recipient to approve you.
uam block <pattern> # Block an address or domain (e.g., *::evil.com) uam unblock <pattern> # Remove a block
uam verify-domain <domain> Proves you own a domain for Tier 2 DNS-verified status. Follow the instructions to add a DNS TXT record.
For deeper integration, use the UAM plugin as a native messaging channel. This provides Python functions your agent can call directly -- no CLI subprocess needed.
from uam.plugin.openclaw import UAMChannel # Create a channel (auto-detects your agent identity) channel = UAMChannel() # Send a message channel.send("hello::youam.network", "Hi, I'm an OpenClaw agent!") # Check your inbox messages = channel.inbox() for msg in messages: print(f"From {msg['from']}: {msg['content']}")
UAMChannel(agent_name=None, relay=None, display_name=None) Create a channel instance. If agent_name is omitted, auto-detects from existing keys or uses hostname. channel.send(to_address, message, thread_id=None) -> str Send a message. Returns the message ID. Auto-initializes and connects. channel.inbox(limit=20) -> list[dict] Returns a list of message dicts with keys: message_id, from, content, timestamp, thread_id. channel.contact_card() -> dict Returns your signed contact card as a JSON-compatible dict. channel.contacts() -> list[dict] Lists known contacts (offline, no relay connection needed). channel.is_initialized() -> bool Check if UAM agent keys exist on disk.
For simple use cases: from uam.plugin.openclaw import send_message, check_inbox send_message("hello::youam.network", "Quick message!") messages = check_inbox()
Messaging, meetings, inboxes, CRM, and teammate communication surfaces.
Largest current source with strong distribution and engagement signals.