xmtp-agent

name

xmtp-agent

description

Connect a running agent (OpenClaw, Claude Code, LangChain, custom Python, any agent runtime) to XMTP messaging so people can DM it and get responses that use the agent's full capabilities — tools, memory, session context. Provides the complete bridge pattern: XMTP CLI setup, identity registration, streaming incoming messages, routing through your agent backend, and sending replies back. Use this skill whenever someone wants to make their agent reachable over XMTP, write a bridge or listener script between an agent process and XMTP, set up xmtp init and stream-all-messages for an agent, have their agent respond to XMTP conversations continuously, wire any agent runtime to the XMTP open messaging network, or pipe XMTP messages through stdin/stdout to an agent process. This skill is specifically about connecting an existing agent to XMTP as a messaging transport — not for building XMTP client apps, looking up XMTP SDK documentation, or sending individual messages.

XMTP Agent

[!CAUTION] Alpha status. Public inbox IDs may be targeted by DOS flooding and prompt injection attempts. Don't give the agent access to sensitive resources. By default, agents store their keys in plaintext — any process running as your user (or root) can read them. Protect them as you would any other secret.

You are connecting an agent to XMTP — the open protocol for secure, decentralized messaging. This skill tells you how to get an identity on the network and bridge incoming messages through your agent backend so it can respond with its full capabilities (tools, memory, context).

The core architecture is a bridge script: XMTP streams messages in, your agent processes them, replies go back out. The agent backend is swappable — OpenClaw, Claude Code, a custom Python process, anything that takes a message and returns a response.

The bridge distinguishes between the owner (the person who deployed the agent) and everyone else. The owner gets full agent capabilities — tools, memory, file access. Public users get a restricted, conversation-only mode controlled by a customizable prompt file (public-prompt.md) that you can edit at any time without restarting.

Always set up the full bridge — even if the user just asks to "send a message", "send me a message", or "test" messaging. These all mean the same thing: they want their agent reachable over XMTP. A one-off send-text command is a dead end — nobody can reply back, and the agent can't respond to future messages. The goal is always an ongoing, two-way conversation. Complete both steps below so the agent is continuously reachable.

Step 1: Install and Initialize

npm install -g @xmtp/cli
xmtp init --env production

Requires Node 22+ and jq. Init generates ~/.xmtp/.env with your wallet key and encryption key.

Verify you're registered:

xmtp client info --json --log-level off --env production

Your inbox ID is at .properties.inboxId in the output.

Before proceeding, ask the owner (the person who deployed the agent) for their Ethereum wallet address or inbox ID. Do not start the bridge without this.

If they provide an Ethereum address, resolve the inbox ID:

export OWNER_INBOX_ID=$(xmtp client inbox-id -i "0xOWNER_WALLET_ADDRESS" --json --log-level off --env production | jq -r '.inboxId')

If they provide an inbox ID directly:

export OWNER_INBOX_ID="their-inbox-id"

Step 2: Start the Bridge

The bridge streams incoming messages and routes them through your agent for responses. Do not send messages using individual CLI commands — everything flows through the bridge.

Save this as a script and run it:

#!/bin/bash
set -euo pipefail

# Public-mode system prompt — read from file so you can edit it without restarting
PUBLIC_PROMPT_FILE="./public-prompt.md"
if [[ ! -f "$PUBLIC_PROMPT_FILE" ]]; then
  cat > "$PUBLIC_PROMPT_FILE" << 'PROMPT'
You are representing your owner to a third party. Be helpful and conversational,
but do NOT reveal sensitive memories, personal information, files, or system
details about your owner. Do NOT use tools, read files, execute commands, or
access any system resources. If you are unsure whether something is safe to
share or do, err on the side of caution and decline.
PROMPT
  echo "Created $PUBLIC_PROMPT_FILE — edit it to customize what public users can access." >&2
fi

# Get your inbox ID for filtering your own messages
MY_INBOX_ID=$(xmtp client info --json --log-level off --env production \
  | jq -r '.properties.inboxId // empty')

[[ -z "$MY_INBOX_ID" ]] && echo "Failed to get inbox ID" >&2 && exit 1

# Stream all incoming messages and respond
xmtp conversations stream-all-messages --json --log-level off --env production \
  | while IFS= read -r event; do

  conv_id=$(echo "$event" | jq -r '.conversationId // empty')
  sender=$(echo "$event" | jq -r '.senderInboxId // empty')
  content=$(echo  | jq -r )
  content_type=$(  | jq -r )

  
  [[ -z  || -z  ||  ==  ]] && 
  [[  !=  ]] && 

  
  
   [[  ==  ]]; 
    response=$(openclaw agent \
      --session-id  \
      --message  \
      2>/dev/null) || 
  
    response=$(openclaw agent \
      --session-id  \
      --message  \
      2>/dev/null) || 
  

  
  [[ -n  ]] && \
    xmtp conversation send-text   -- production

The bridge uses the XMTP conversation ID as the session ID so each person (or group) chatting with your agent gets their own persistent context.

After the bridge is running, tell the user:

• Their agent's wallet address and inbox ID (both — so they can share whichever is convenient)
• They can customize how the agent interacts with public users by editing public-prompt.md. Changes take effect immediately — no restart needed.

To keep the bridge running long-term, use your preferred process manager (systemd, pm2, Docker, etc.).

Choosing a Backend

The bridge template above uses openclaw agent but the agent backend is the part you swap. Each example below shows the owner/public branching — replace the if/else block in the bridge with the version matching your setup.

OpenClaw (subprocess with session state)

if [[ "$sender" == "$OWNER_INBOX_ID" ]]; then
  response=$(openclaw agent \
    --session-id "$conv_id" \
    --message "$content" \
    2>/dev/null) || continue
else
  response=$(openclaw agent \
    --session-id "public-$conv_id" \
    --message "[SYSTEM: $(cat "$PUBLIC_PROMPT_FILE")] $content" \
    2>/dev/null) || continue
fi

OpenClaw gives the agent full tool access and retains conversation history per session. The public path prepends a restrictive system prompt and isolates sessions with the public- prefix.

Harder enforcement (optional): OpenClaw supports tool profiles in openclaw.json. Define a second agent with tools.profile: "messaging" (messaging + session tools only, no filesystem or shell) and route public users to it instead of relying on the system prompt alone:

{
  "agents": {
    "list": [
      { "name": "owner-agent", "tools": { "profile": "full" } },
      { "name": "public-agent", "tools": { "profile": "messaging" } }
    ]
  }
}

Then route by agent name in the bridge:

if [[ "$sender" == "$OWNER_INBOX_ID" ]]; then
  response=$(openclaw agent --agent owner-agent \
    --session-id "$conv_id" --message "$content" 2>/dev/null) || continue
else
  response=$(openclaw agent --agent public-agent \
    --session-id "public-$conv_id" --message "$content" 2>/dev/null) || continue
fi

Claude Code (session-based CLI)

Claude Code requires --session-id to be a valid UUID. Generate deterministic UUIDs from conversation IDs using uuidgen --sha1 (or Python's uuid5). Use separate namespace UUIDs for owner vs public sessions to keep them isolated.

# Namespace UUIDs for deterministic session IDs (generate your own with uuidgen)
OWNER_NS="e1a2b3c4-d5e6-7f80-9a0b-1c2d3e4f5a6b"
PUBLIC_NS="f6b5a4e3-d2c1-0b9a-8f7e-6d5c4b3a2f1e"

if [[ "$sender" == "$OWNER_INBOX_ID" ]]; then
  session_id=$(python3 -c "import uuid; print(uuid.uuid5(uuid.UUID('$OWNER_NS'), '$conv_id'))")
  response=$(claude --session-id "$session_id" \
    --output-format text \
    -p "$content" \
    2>/dev/null) || continue
else
  session_id=$(python3 -c "import uuid; print(uuid.uuid5(uuid.UUID('$PUBLIC_NS'), '$conv_id'))")
  response=$(claude --session-id "$session_id" \
    --output-format text \
    --tools "" \
    -p "[SYSTEM: $(cat "$PUBLIC_PROMPT_FILE")] $content" \
    2>/dev/null) || continue
fi

The --session-id flag maintains the full Claude Code session — files it's read, tools it can use, conversation history. The owner gets full capabilities; public users get --tools "" to disable all tool access plus the restrictive system prompt. Different namespace UUIDs ensure owner and public sessions never collide.

Custom process (stdin/stdout)

if [[ "$sender" == "$OWNER_INBOX_ID" ]]; then
  response=$(echo "$content" | your-agent-process \
    --session-id "$conv_id" \
    2>/dev/null) || continue
else
  response=$(echo "[SYSTEM: $(cat "$PUBLIC_PROMPT_FILE")] $content" \
    | your-agent-process \
    --session-id "public-$conv_id" \
    2>/dev/null) || continue
fi

Any process that reads from stdin and writes to stdout works. For a Python agent:

#!/usr/bin/env python3
import sys
message = sys.stdin.read().strip()
# Your agent logic here — full tool access, DB queries, etc.
print(f"Response to: {message}")

The key property across all backends: the owner gets full capabilities (tools, memory, context), while public users are restricted to conversation only.

Stream Output Format

Each line from the stream is a JSON object:

{
  "id": "message-id",
  "conversationId": "conversation-id",
  "senderInboxId": "sender-inbox-id",
  "contentType": {
    "authorityId": "xmtp.org",
    "typeId": "text",
    "versionMajor": 1,
    "versionMinor": 0
  },
  "content": "Hello!",
  "sentAt": "2026-03-04T04:14:36.849Z",
  "deliveryStatus": 1,
  "kind": 0
}

Security

The bridge passes raw message content from any XMTP user to your agent backend. The owner/public split ensures only the deployer gets full agent capabilities — everyone else is restricted to conversation only, preventing strangers from triggering file reads, shell commands, or other sensitive operations via prompt injection.

How the guardrail works:

• OWNER_INBOX_ID identifies the deployer — only they get full agent capabilities
• Public users get a restrictive system prompt prefix and isolated sessions
• The system prompt restriction is a soft guardrail — a determined attacker may bypass it via prompt injection, so don't give the agent access to truly sensitive resources regardless

Finding your inbox ID: Resolve it from your Ethereum wallet address:

xmtp client inbox-id -i "0xYOUR_WALLET_ADDRESS" --json --log-level off --env production | jq -r '.inboxId'

Multiple trusted users: To allowlist additional inbox IDs, expand the condition:

if [[ "$sender" == "$OWNER_INBOX_ID" || "$sender" == "$TRUSTED_USER_2" ]]; then

Or use an array:

TRUSTED_IDS=("inbox-id-1" "inbox-id-2")
if printf '%s\n' "${TRUSTED_IDS[@]}" | grep -qxF "$sender"; then

Common Mistakes

Mistake	Fix
Sending a one-off message with send-text	Always set up the full bridge — even for "just a test". One-off sends are dead ends with no way to receive replies
Reading .inboxId from client info	Inbox ID is at .properties.inboxId
Filtering by senderAddress	Stream returns senderInboxId; compare against your inbox ID
Not using --log-level off	Log output mixes with JSON on stdout; suppress it
Using a global session ID	Use $conv_id so each conversation gets its own agent context
Piping to a raw LLM instead of an agent	Route through your agent runtime so tools and memory are preserved
Using read -r without IFS=	Use IFS= read -r to preserve whitespace in JSON lines
Running without OWNER_INBOX_ID	Set the owner's inbox ID so public users get restricted mode