Pilot Protocol

The network stack for AI agents.
Addresses. Ports. Tunnels. Encryption. Trust.

Docs  ·  Wire Spec  ·  Whitepaper  ·  IETF Draft  ·  Agent Skills  ·  Polo (Live Dashboard)

The internet was built for humans. AI agents have no address, no identity, no way to be reached. Pilot Protocol is an overlay network that gives agents what the internet gave devices: a permanent address, authenticated encrypted channels, and a trust model -- all layered on top of standard UDP.

Agents register with a rendezvous service for discovery and NAT traversal. Application data flows directly between peers -- never through a central server. It is not an API. It is not a framework. It is infrastructure.

The problem

Today, agents talk through centralized APIs. Every message passes through a platform -- the platform sees all traffic, controls access, and becomes a single point of failure.

graph LR
    A1[Agent A] -->|HTTP API| P[Platform / Cloud]
    A2[Agent B] -->|HTTP API| P
    A3[Agent C] -->|HTTP API| P
    style P fill:#f66,stroke:#333,color:#fff
    style A1 fill:#4a9,stroke:#333,color:#fff
    style A2 fill:#4a9,stroke:#333,color:#fff
    style A3 fill:#4a9,stroke:#333,color:#fff

Pilot Protocol takes the platform out of the data path. A lightweight rendezvous service handles discovery and NAT traversal, but once agents find each other, they talk directly over authenticated, encrypted tunnels:

graph LR
    A1[Agent A<br/><small>0:0000.0000.0001</small>] <-->|Encrypted UDP Tunnel| A2[Agent B<br/><small>0:0000.0000.0002</small>]
    A1 <-->|Encrypted UDP Tunnel| A3[Agent C<br/><small>0:0000.0000.0003</small>]
    A2 <-->|Encrypted UDP Tunnel| A3
    A1 -.->|discovery| RV[Rendezvous]
    A2 -.->|discovery| RV
    A3 -.->|discovery| RV
    style A1 fill:#4a9,stroke:#333,color:#fff
    style A2 fill:#4a9,stroke:#333,color:#fff
    style A3 fill:#4a9,stroke:#333,color:#fff
    style RV fill:#888,stroke:#333,color:#fff

What agents get

pilotctl info
pilotctl set-hostname my-agent
pilotctl find other-agent
pilotctl send other-agent 1000 --data "hello"
pilotctl recv 1000 --count 5 --timeout 30s

from pilotprotocol import Driver

with Driver() as d:
    info = d.info()
    d.set_hostname("my-agent")
    peer = d.resolve_hostname("other-agent")
    with d.dial("other-agent:1000") as conn:
        conn.write(b"hello")
        data = conn.read(4096)

Every CLI command supports --json for structured output. The Python SDK wraps the Go driver via ctypes FFI. See examples/python_sdk/ for PydanticAI integration and more.

$ pilotctl --json info
{"status":"ok","data":{"address":"0:0000.0000.0005","node_id":5,"hostname":"my-agent","peers":3,"connections":1,"uptime_secs":3600}}

$ pilotctl --json find other-agent
{"status":"ok","data":{"hostname":"other-agent","address":"0:0000.0000.0003"}}

$ pilotctl --json recv 1000 --count 1
{"status":"ok","data":{"messages":[{"seq":0,"port":1000,"data":"hello","bytes":5}]}}

$ pilotctl --json find nonexistent
{"status":"error","code":"not_found","message":"hostname not found: nonexistent","hint":"check the hostname and ensure mutual trust exists"}

Highlights

Architecture

graph LR
    subgraph Local Machine
        Agent[Your Agent] -->|commands| CLI[pilotctl]
        CLI -->|Unix socket| D[Daemon]
        D --- E[Echo :7]
        D --- DX[Data Exchange :1001]
        D --- ES[Event Stream :1002]
        D --- TS[Task Submit :1003]
    end

    D <====>|UDP Tunnel<br/>AES-256-GCM + NAT traversal| RD

    subgraph Remote Machine
        RD[Remote Daemon] -->|Unix socket| RC[pilotctl]
        RC -->|commands| RA[Remote Agent]
        RD --- RE[Echo :7]
        RD --- RDX[Data Exchange :1001]
        RD --- RES[Event Stream :1002]
        RD --- RTS[Task Submit :1003]
    end

    D -.->|register + discover| RV
    RD -.->|register + discover| RV

    subgraph Rendezvous
        RV[Registry :9000<br/>Beacon :9001]
    end

Your agent talks to a local daemon over a Unix socket. The daemon handles tunnel encryption, NAT traversal, packet routing, congestion control, and built-in services. The daemon maintains a connection to a rendezvous server (registry + beacon) for node registration, peer discovery, and NAT hole-punching. Once a tunnel is established, data flows directly between daemons -- the rendezvous is not in the data path.

A public rendezvous is provided at 34.71.57.205:9000, or you can run your own with rendezvous -registry-addr :9000 -beacon-addr :9001.

For connection lifecycle details, gateway bridging, and NAT traversal strategy, see the full documentation.

Demo

A public demo agent (agent-alpha) is running on the network with auto-accept enabled:

# 1. Install
curl -fsSL https://pilotprotocol.network/install.sh | sh

# 2. Start the daemon
pilotctl daemon start --hostname my-agent --email user@example.com

# 3. Request trust (auto-approved within seconds)
pilotctl handshake agent-alpha "hello"

# 4. Wait a few seconds, then verify trust
pilotctl trust

# 5. Start the gateway (maps the agent to a local IP)
sudo pilotctl gateway start --ports 80 0:0000.0000.0004

# 6. Open the website
curl http://10.4.0.1/

You can also ping and benchmark:

pilotctl ping agent-alpha
pilotctl bench agent-alpha

Install

curl -fsSL https://pilotprotocol.network/install.sh | sh

Set a hostname and email during install:

curl -fsSL https://pilotprotocol.network/install.sh | PILOT_EMAIL=user@example.com PILOT_HOSTNAME=my-agent sh

Python SDK

pip install pilotprotocol

See the Python SDK documentation for the full API reference.

Testing

go test -parallel 4 -count=1 ./tests/

845 tests pass. The -parallel 4 flag is required -- unlimited parallelism exhausts ports and causes dial timeouts.

Documentation

License

Pilot Protocol is licensed under the GNU Affero General Public License v3.0.

Vulture Labs
_{Built for agents, by humans.}