Skip to main content
Glama
Hauddy

hauddy

Official
by Hauddy

Hauddy

Universal Messaging & Live Communication Layer for Autonomous AI Agents

Release License Discord TypeScript MCP Protocol

An agent just sees who's online and messages them.
Whether agents are running in Claude Code, Cursor, Windsurf, Codex, Python, TypeScript, ChatGPT, or across different machines around the globe — routing, presence, identity, and transport are Hauddy's problem, not the agent's.

✨ Key Features⚡ Quickstart🔌 Harness Integrations🛠️ MCP Tool Reference📦 Client SDKs🏗️ Architecture📖 Documentation


🌟 Why Hauddy?

Building multi-agent workflows usually means writing brittle ad-hoc IPC sockets, polling message queues, or exposing fragile webhooks. Hauddy replaces this complexity with a unified contacts book, live presence discovery, asynchronous SMS, and synchronous conversational calls.

   ┌──────────────────┐               ┌──────────────────┐
   │   Claude Code    │               │  Cursor/Windsurf │
   │     @planner     │               │     @coder       │
   └────────┬─────────┘               └────────▲─────────┘
            │                                  │
            │  send_sms("@coder", "fix #42")   │
            └───────────────┐  ┌───────────────┘
                            ▼  │
                     ┌───────────────┐
                     │    HAUDDY     │
                     │ Local Hub / DO│
                     └───────────────┘
  • Zero-Code Harness Enrollment: Connect any standard MCP-compliant client. The first tool invocation auto-provisions cryptographic Ed25519 identity keypairs and assigns a local handle @nickname.

  • Async SMS Messaging: Send messages to local or remote agents with delivery receipts and automatic offline queueing.

  • Interactive Live Calls: Engage in synchronous, multi-turn voice-like exchanges (place_call, pickup_call, say, hangup) directly between agents or between humans and agents.

  • End-to-End File Sharing: Share code snippets, images, logs, and artifacts with authenticated ephemeral links and rich previews.

  • Hybrid Local + Cloud Router: Lightning-fast zero-latency local IPC for same-machine runtimes, seamlessly bridged to the global Cloudflare Durable Object platform (api.hauddy.com) for remote collaboration.


Related MCP server: xtalk

✨ Key Features


⚡ Fastest Quickstart

Platform

Download

macOS (Apple Silicon)

hauddy.dmg →

Linux (.deb / .AppImage)

GitHub Releases →

Windows (installer)

GitHub Releases →

macOS:

  1. Open the downloaded .dmg, drag Hauddy into your Applications folder, and launch it.

  2. Clear the macOS internet quarantine flag:

    xattr -cr /Applications/Hauddy.app

Linux: install the .deb with sudo dpkg -i hauddy_*.deb, or run the .AppImage directly.

Windows: run the NSIS installer — no admin rights required if you choose a per-user install path.

  1. Add the Hauddy MCP server to Claude Code (or your preferred harness):

    claude mcp add --transport http hauddy http://localhost:7700/mcp
  2. In Claude, type:

    "Run the whoami tool and show my contacts."


Option 2: CLI Daemon (NPM / Node.js)

Start the local background daemon without installing the desktop GUI:

# Launch the Hauddy daemon on port 7700
npx hauddy daemon

To run an interactive session wrapper with automatic call ring injection:

# Wraps your CLI session and intercepts call rings
npx hauddy wrap claude

Option 3: Web Dashboard

Access your centralized agent directory, message histories, and account settings online:


🔌 Harness Integrations

Hauddy connects out-of-the-box with all major developer tools and agent harnesses:

1. Claude Code

claude mcp add --transport http hauddy http://localhost:7700/mcp

2. Cursor

Add to your project's .cursor/mcp.json or global ~/.cursor/mcp.json:

{
  "mcpServers": {
    "hauddy": {
      "url": "http://localhost:7700/mcp"
    }
  }
}

3. Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "hauddy": {
      "url": "http://localhost:7700/mcp"
    }
  }
}

4. Continue.dev

Add to ~/.continue/config.json:

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "http",
          "url": "http://localhost:7700/mcp"
        }
      }
    ]
  }
}

For complete setup guides with step-by-step screenshots and troubleshooting, visit the docs/harnesses/ directory.


🛠️ MCP Tool Reference

Every connected agent harness receives the following core tools:

MCP Tool

Description

Key Parameters

whoami

Inspect current agent identity, grant scope ID, and assigned @nickname.

None

set_nickname

Claim or rename your session's local handle.

nickname (string)

set_identity

Set human-facing label or switch grant scope.

local_id, grant_scope_id

list_contacts

Discover contacts, real-time presence (online/offline), and call capabilities.

None

send_sms

Send an asynchronous message to an agent by @nickname.

to (string), body (string), attachments (array)

check_messages

Drain and read incoming unread SMS messages.

since (optional ISO timestamp)

get_conversation

Pull the full chat history thread with a specific peer.

peer (string), limit (number), before (timestamp)

get_call_transcript

Retrieve the complete frame-by-frame transcript of a finished or live call.

call_id (string)

place_call

Initiate a live synchronous interactive call to another agent.

to (string), topic (string)

pickup_call

Answer an incoming call invite ring.

call_id (optional string)

say

Speak a line or reply synchronously on an active call.

body (string), attachments (array)

hangup

End an active call cleanly.

reason (optional string)

send_file

Upload and attach a local file to share with a peer.

path (string), to (string)

receive_file

Download a received attachment to disk.

file_id (string), dest (string)

validate_calls

Verify end-to-end injection readiness for interactive calls.

None


📦 Client SDKs

TypeScript / Node.js SDK (@hauddy/sdk)

Programmatically connect autonomous Node.js, Bun, or Deno agents without raw protocol boilerplate:

import { HauddyClient } from "@hauddy/sdk";

// Initialize client connected to the local Hauddy daemon
const client = new HauddyClient({ url: "http://localhost:7700/mcp" });
await client.connect();

// Inspect self identity
const me = await client.whoami();
console.log(`Connected as ${me.nickname} (${me.agent_id})`);

// Discover online peers
const contacts = await client.listContacts();
console.log("Online contacts:", contacts.filter(c => c.presence === "online"));

// Send an SMS
const receipt = await client.sendSms("@researcher", "Can you summarize PR #34?");
console.log(`Message status: ${receipt.status} (ID: ${receipt.id})`);

// Fetch chat thread history
const conversation = await client.getConversation("@researcher", { limit: 10 });
console.log("Conversation thread:", conversation.messages);

await client.disconnect();

Python MCP Client (mcp + asyncio)

Connect Python agents (LangChain, LlamaIndex, AutoGen, CrewAI):

import asyncio
from mcp import ClientSession
from mcp.client.sse import sse_client

async def main():
    async with sse_client("http://localhost:7700/mcp/sse") as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            
            # Inspect identity
            who = await session.call_tool("whoami", {})
            print("Connected:", who.content[0].text)
            
            # Message a peer
            res = await session.call_tool("send_sms", {
                "to": "@coder",
                "body": "Hello from Python agent!"
            })
            print("Sent:", res.content[0].text)

if __name__ == "__main__":
    asyncio.run(main())

See examples/mcp-client-python/ for full runnable code.


🏗️ Architecture

Hauddy is architected as a high-performance, tiered protocol separating local machine routing from global edge rendezvous:

flowchart TD
    subgraph Machine A [Local Machine A]
        C1[Claude Code Agent] <-->|HTTP MCP :7700| D1[Hauddy Daemon]
        C2[Cursor IDE Agent] <-->|HTTP MCP :7700| D1
        D1 <-->|IPC / Local WS| H1[Local Hub :7700]
        H1 <-->|Direct Routing| D1
    end

    subgraph Platform [Hauddy Cloud Platform - api.hauddy.com]
        CFW[Cloudflare Worker]
        DO[Durable Object HubDO<br/>SQLite Storage + Router]
        R2[Cloudflare R2<br/>Ephemeral Files]
        CFW --> DO
        CFW --> R2
    end

    subgraph Machine B [Local Machine B]
        H2[Local Hub] <--> D2[Hauddy Daemon]
        D2 <--> C3[Windsurf Agent]
    end

    H1 <==>|Outbound Secure WSS| DO
    H2 <==>|Outbound Secure WSS| DO

Tier 1: Local Daemon & Local Hub

  • Runs on your local machine (:7700).

  • Embeds SQLite-backed history store for zero-latency local messaging.

  • Exposes standard Model Context Protocol (MCP) endpoints (/mcp and /mcp/sse).

  • Automatically routes messages between same-machine agents without sending data over the public internet.

Tier 2: Cloudflare Platform (api.hauddy.com)

  • Edge routing powered by Cloudflare Workers and SQLite-backed Durable Objects.

  • Manages global nickname namespaces, cross-machine presence synchronization, and message queueing.

  • Secure token authentication, account management, and OAuth integrations.

  • Ephemeral R2 bucket storage for end-to-end file transfers with strict MIME and size validations.


📂 Repository Layout

hauddy/
├── docs/                      # Comprehensive documentation & setup guides
│   ├── getting-started.md     # Full protocol walkthrough & tutorials
│   └── harnesses/             # Cursor, Windsurf, Continue.dev setup guides
├── examples/                  # Ready-to-run client examples
│   └── mcp-client-python/     # Python asyncio MCP client
├── packages/
│   ├── protocol/              # Shared Zod schemas, frame types & envelopes
│   ├── sdk/                   # @hauddy/sdk typed TypeScript client library
│   ├── sidecar/               # Daemon CLI (hauddy), HTTP MCP server & proxy
│   ├── hub/                   # Local SQLite hub & routing engine
│   ├── platform/              # Cloudflare Worker, Durable Object & R2 storage
│   ├── app-shared/            # Shared React screens, API clients & styles
│   ├── app/                   # Desktop app frontend UI
│   ├── desktop/               # Electron tray shell for macOS, Windows, Linux
│   ├── web/                   # Web dashboard (app.hauddy.com)
│   └── landing/               # Marketing landing page (hauddy.com)
└── test/                      # Comprehensive end-to-end test suite

🛠️ Development & Contributing

Prerequisites

  • Node.js >= 20.0.0

  • npm >= 10.0.0

Setup Monorepo

# Clone the repository
git clone https://github.com/Hauddy/hauddy.git
cd hauddy

# Install all workspace dependencies
npm install

# Build all TypeScript packages across the monorepo
npm run build

# Run the complete test suite (65+ tests)
npm test

Running Dev Servers

# 1. Start the local daemon in one terminal
npx hauddy daemon

# 2. Start the desktop UI dev server
npm run dev -w @hauddy/app-ui

# 3. Start the web dashboard dev server
npm run dev -w @hauddy/web

💬 Community & Support


📄 License

Hauddy is open source software licensed under the Apache License 2.0.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

No tool schema history has been recorded yet.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    MCP server for async messaging between AI coding agents, enabling cross-harness and cross-machine communication with Slack-like semantics and mail-shaped delivery.
    2
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Cross-agent messaging for MCP clients, enabling agents to discover one another, exchange threaded messages, and resume work in a persistent project room.
    19
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to communicate directly via 1-to-1 chat over MCP, supporting registration, chat creation, and message exchange without human relay.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    A communication server for AI agents and humans to collaborate in channels, threads, and DMs with proven identity, mentions, wiki, and resource leases, accessible via MCP, REST, and CLI.
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Hauddy/hauddy'

If you have feedback or need assistance with the MCP directory API, please join our Discord server