An open protocol for discovering A2A-capable agents on local networks.

LAD-A2A addresses a critical gap in the AI agent ecosystem: when a device joins a network—hotel Wi-Fi, office LAN, cruise ship, hospital campus—how does the user's AI assistant discover and connect to local agents? While A2A defines agent-to-agent communication and MCP defines agent-to-tool integration, LAD-A2A defines agent discovery.

With LAD-A2A, agents can:

• Automatically discover local A2A agents when joining a network
• Verify identity through signed AgentCards and DIDs
• Obtain user consent before establishing connections
• Negotiate capabilities via standard A2A mechanisms

AI agents are increasingly capable, but they remain isolated from their physical environment. A guest's AI assistant has no way to discover the hotel's concierge agent. An employee's assistant can't find the building's room booking agent. A patient's assistant doesn't know the hospital offers a wayfinding agent.

LAD-A2A solves this by providing:

• Zero-Configuration Discovery: Agents find each other automatically via mDNS/DNS-SD, well-known endpoints, or DHCP options.
• Defense in Depth: Local networks are hostile by default. LAD-A2A requires TLS, signed AgentCards, verifiable identities (DIDs), and explicit user consent.
• Graceful Degradation: Multiple discovery mechanisms ensure compatibility from consumer Wi-Fi to enterprise networks.
• Ecosystem Alignment: LAD-A2A only handles discovery—once an agent is found, standard A2A communication takes over.

LAD-A2A is the first handshake. It answers "who's here?" so that A2A can answer "what can you do?" and MCP can answer "how do I do it?"

LAD-A2A supports multiple discovery paths with automatic fallback:

Experience LAD-A2A with a fully working demo featuring two AI agents:

cd demo
cp .env.example .env
# Add your OpenAI API key to .env
./run_demo.sh

Open http://localhost:8000 to see:

• Real mDNS discovery (_a2a._tcp.local)
• LAD-A2A protocol in action
• A2A JSON-RPC 2.0 communication
• LLM-based query routing

See demo/README.md for full documentation.

cd reference
pip install -e .

# Start a discovery server (development only)
python -m server.lad_server --name "My Agent" --port 8080

# Discover agents (in another terminal)
python -m client.lad_client --url http://localhost:8080

Note: The example above uses HTTP for local development. In production, TLS is required per the security spec. All HTTP endpoints MUST use TLS 1.2+.

1. Guest device joins "ExampleHotel-Guest" Wi-Fi
2. Client queries mDNS for _a2a._tcp.local
   └─ Fallback: GET https://portal.examplehotel.com/.well-known/lad/agents
3. Discovery response includes AgentCard URL
4. Client fetches and verifies AgentCard (signed, DID-bound)
5. Client prompts user: "Hotel Concierge agent found. Connect?"
6. User approves → Standard A2A session begins
7. User asks: "What time is breakfast?" → Agent responds via A2A

Local networks are hostile by default. LAD-A2A mandates:

📚 Full documentation at lad-a2a.org

We welcome contributions to enhance the LAD-A2A protocol.

• Questions & Discussions: GitHub Discussions
• Issues & Feedback: GitHub Issues
• Contribution Guide: CONTRIBUTING.md

This project is licensed under the Apache License 2.0.