A2AL Daemon

io.github.a2alPublished by GitHub account a2alv0.2.7Updated Oct 24, 2026

Makes any AI agent globally reachable and discoverable—no cloud, domain, or port forwarding needed.

Overview

AI-generated overview

A local daemon that gives AI agents a self-owned address so they can find and connect to each other directly across NAT, machines and sleep cycles.

What you can do
Resolve and reach other agents by their self-sovereign AID address, fetching remote endpoints such as agent metadata over HTTP through the local daemon at port 2121, with no cloud, domain or port forwarding required. Send encrypted notes to an agent whose machine may be offline, and exchange chat messages after an invite. Coordinate in rooms whose history persists for members who were offline, and share files. Expose a local HTTP service to others through an inbound binding, and manage identities, access control and tunnels. Wire the daemon into MCP hosts such as Claude Code, VS Code, Cursor and Claude Desktop, either over the local HTTP endpoint or by spawning the stdio proxy.
When to use it
Use it when agents or people on different machines need to reach each other without a VPN, public IP or tunnel service, or when you want to leave work for a machine that is asleep and have it picked up later. It suits multi-agent coordination and file sharing where a vendor workspace is undesirable.
Requirements
A local a2ald daemon on the user's machine, installed as a standalone binary, via npm install -g a2ald, or as a Linux package; the MCP server is either the daemon's local HTTP endpoint or the a2ald stdio proxy, which needs a running daemon. An identity must be created in the Web UI. By default the daemon joins the public Tangled Network; a private network can be set up with your own bootstrap seeds. Desktop only.
Before you install
The daemon joins the public Tangled Network by default, so review what is visible and enable only the channels you need. Identities are key-based and self-sovereign, so the key behind an AID is the credential to protect. It can send notes, chat messages and room entries, bind local HTTP services for outside callers, and share files, all of which expose data to other agents. The Windows binary is unsigned and triggers SmartScreen. The project states it is not tied to any token or financial offer.

Installation

In SourceWeft

  1. Open A2AL Daemon in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

A2AL — Agent-to-Agent Link

[npm] [PyPI] [Go Reference] [License: MPL 2.0]

Peer-to-peer networking protocol for multi-agent AI — reach any agent, across NAT, machines, and sleep cycles, with no relay server and no cloud dependency. Open source, MPL-2.0.

Official sites: a2al.org · Tangled Network · tngld.net

Always reachable. Give an AI agent, app, device, or person a reachable address — then find others and connect directly, across NAT and machine boundaries. No domain. No cloud account. No central registry.

Your key, your address. That address is an AID: it comes from a key you hold. Nobody issues it, revokes it, or reassigns it. You hand it over once. They still reach you when the laptop changes Wi-Fi, the box moves, or the machine was asleep when they first tried. After connect, application bytes go peer-to-peer; A2AL is not in the data path.

The missing layer. MCP, A2A, ANP, and the rest already know how AI agents talk once they have a URL. None of them say how a laptop, a home server, and a worker in a vendor-less world share one address that survives the next NAT, the next cloud, the next company — across agentic workflows and multi-agent systems alike. That layer is missing. A2AL is that layer, and it has to live in the open — an address you own is only real if no one vendor has to stay up for you to exist.

One daemon, full stack. a2ald runs on your machine, open source: agent identities, direct cross-machine connections, Web UI, REST API, and a built-in MCP server. It joins the public Tangled Network by default. Prefer a network only your machines belong to? --bootstrap your own seeds; the same addressing, notes, and rooms.

[A2AL peer-to-peer networking: create an AI agent identity (AID) in the Web UI, then call other agents by address across machines]

Start

Person — download A2AL for your system, extract it, and run a2ald — a single binary, ~17 MB, no installer or runtime needed. The Web UI opens automatically. Create an identity; that is enough to begin.

(Windows: SmartScreen shows "More info → Run anyway" on first launch — this is expected for an unsigned open-source binary.)

To stay reachable after closing the terminal: Windows/macOS a2ald service install; Linux deploy/linux.

Agent — if a daemon endpoint is already available, connect through the a2al CLI, REST API, or MCP. Otherwise download the binaries from Releases and run a2ald --no-open-browser. Full guide: Agent Install.

Using an MCP host? a2ald mcp add wires it in; a2ald mcp print gives the entry to place by hand. Details: MCP Setup.

Already have their AID — any HTTP client:

text
http://127.0.0.1:2121/aid/{AID}/…

There is no warm-up gate. The daemon answers locally as soon as it is up. Call others right away.

Other installation options: npm install -g a2ald (Node.js daemon/MCP server) · .deb / .rpm (Linux service) · pip install a2al (Python SDK with sidecar). Full path: Quick Start.

When it's worth it

JobOtherwiseWith A2AL
Reach something on someone else's laptopVPN, public IP, rotating tunnel URLThey send an AID once; you fetch
Let others call your local HTTPDomain+TLS, or a hostname you must redistributea2al inbound bind --addr 127.0.0.1:8080
Leave work for a machine that is asleepSlack the human, or a webhook 404Encrypted note to their AID
Agents (and people) coordinating, sharing filesVendor workspace; everyone onlineA room — history stays after someone was offline
Ongoing 1:1IM product, or notes-as-chatChat (invite first)
Stay off the public directoryTailscale / homemade VPN--bootstrap your seeds

MCP

HTTP (recommended — REST and the Web UI come with it):

json
{  "mcpServers": {    "a2al": {      "url": "http://127.0.0.1:2121/mcp/"    }  }}

a2ald mcp add auto-configures Claude Code, VS Code, Cursor, Claude Desktop, Windsurf, OpenClaw, Hermes, and DeepSeek Harness. Hosts that only spawn a process: "command": "a2ald", "args": ["--mcp-stdio"] (proxies to a running daemon). Setup: MCP Setup. Agent entry: llms.txt.

Everyday CLI

bash
a2al get <AID> /.well-known/agent.jsona2al note send <your-aid> <their-aid> "$(echo -n 'job payload' | base64)"a2al group append --aid <your-aid> --group-id <gid> --kind msg --body '…'a2al inbound bind --addr 127.0.0.1:8080

a2al help for the rest. Numbers (timing, note size, rooms): User Guide.

[Multi-agent collaboration over A2AL: agents coordinate via AIDs with no relay server]

Docs

If you want to…Read
How visible, which channelOnly turn on what you need
Find the right pagedoc/
Wire an MCP hostMCP Setup · MCP entry
Identities, notes, chat, rooms, ACL, tunnelsUser Guide
REST, MCP tools, PythonAPI Reference
Embed in GoGo SDK
Build from sourceDeveloper Guide
Protocol internalsArchitecture
Example binariesExamples

Protocol design

A2AL is an open protocol; a2ald is its reference implementation.

Self-sovereign identity. An AID is derived from a key you generate. No registry issues, revokes, or reassigns it — identity is end-to-end verifiable.

Decentralized discovery. The Tangled Network stores endpoint records, not payloads. Any node can resolve an AID without a central authority; the network operates at any scale.

Mutual authentication. Every connection cryptographically verifies both ends. You always know the agent on the other side is who it claims to be.

Direct communication. A2AL resolves addresses and brokers the initial connection, then steps aside. Application data flows peer-to-peer, not through the protocol.

Web3 compatible. Ethereum wallet addresses work as AIDs. Cross-key attestation lets an agent prove ownership of both a native AID and a blockchain identity — Web3 is supported, not required.

A2AL is complementary to existing agent communication standards:

ProtocolRoleHow A2AL fits
MCPTool-calling interfaceA2AL is an MCP-installable server; agents get addressing and networking as tools
A2AAgent collaboration semanticsA2AL provides the discovery and connectivity layer A2A assumes
ANPAgent networking visionA2AL implements the decentralized network layer ANP envisions

Contributing

If the missing layer is worth having, it is worth building together. Open an issue before significant work. A PR needs a signed Contributor License Agreement; a bot will prompt you.

Disclaimer

A2AL is a networking protocol project. It is not associated with any cryptocurrency token, ICO, or financial product. Any use of the A2AL name or codebase in token offerings or financial promotions is unauthorized and not endorsed by the authors.

Author

XG.Shi — This project is not affiliated with or endorsed by any employer or organization.

License

Copyright (c) 2026 The A2AL Authors. Mozilla Public License 2.0.

Source: README.md at commit 8fc8f8c

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.7LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts