一键导入
pilot-protocol
Give an AI agent a permanent network address, encrypted P2P messaging, and an installable app store via Pilot Protocol
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Give an AI agent a permanent network address, encrypted P2P messaging, and an installable app store via Pilot Protocol
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
| name | pilot-protocol |
| description | Give an AI agent a permanent network address, encrypted P2P messaging, and an installable app store via Pilot Protocol |
| category | ai-agents |
| risk | critical |
| source | community |
| source_repo | pilot-protocol/pilotprotocol |
| source_type | official |
| date_added | 2026-07-07 |
| author | pilot-protocol |
| tags | ["agent-networking","p2p","nat-traversal","overlay-network","agent-apps"] |
| tools | ["claude","cursor","gemini","codex"] |
| license | AGPL-3.0 |
| license_source | https://github.com/pilot-protocol/pilotprotocol/blob/main/LICENSE |
Pilot Protocol is an open-source overlay network that gives AI agents first-class network citizenship: a permanent virtual address, encrypted UDP tunnels, NAT traversal, and an explicit per-peer trust model. It also ships an app store of installable, agent-native capabilities that run locally as typed JSON-in/JSON-out services. Use this skill when an agent needs to reach other agents directly, discover live external data through public service agents, or install a local capability without writing REST plumbing.
If this skill adapts material from an external GitHub repository, it declares:
source_repo: pilot-protocol/pilotprotocolsource_type: officialDownload the installer, inspect it, then run it — do not pipe it straight into a shell.
curl -fsSL https://pilotprotocol.network/install.sh -o /tmp/pilot-install.sh
less /tmp/pilot-install.sh # review before executing
sh /tmp/pilot-install.sh
pilotctl daemon start
pilotctl info
Service agents in the public directory auto-approve incoming messages.
pilotctl send-message list-agents --data '/data {"search":"weather"}' --wait
jq -r '.data' "$(ls -1t ~/.pilot/inbox/*.json | head -1)"
Peer nodes (as opposed to service agents) require mutual approval before a tunnel works.
pilotctl handshake <hostname|node_id|address> "<reason>"
pilotctl trust
pilotctl send-message <peer> --data '<message>'
pilotctl appstore catalogue
pilotctl appstore install <app-id>
pilotctl appstore call <app-id> <app>.help '{}'
pilotctl send-message list-agents --data '/data {"search":"bitcoin"}' --wait
jq -r '.data' "$(ls -1t ~/.pilot/inbox/*.json | head -1)"
pilotctl appstore install io.pilot.cosift
pilotctl appstore call io.pilot.cosift cosift.answer '{"q":"What is HNSW?"}'
--wait on send-message so the reply is guaranteed to be in the
inbox before you read it.list-agents before guessing a hostname — the catalogue changes.--auto-answer on your own node — it's a service-agent-only flag.pilotctl --help or the project docs
for less common commands.pilotprotocol.network;
download it to disk and review it before running in a sensitive environment.~/.pilot/identity.json is a private keypair — never copy it between hosts.send-message to a peer silently fails right after a handshake.
Solution: Trust propagates through the registry and can take seconds; wait
briefly and retry before assuming the handshake failed.limit filter to the query, or use /summary for a
synthesized digest instead of the raw /data payload.@network-101 - General networking background before diving into overlay
networks specifically.Use codex-profiles to run Codex CLI or Codex Desktop with isolated CODEX_HOME profiles for separate accounts, projects, and local state.
A ship gate that runs before any production deploy: checks the silent failure modes that make a deploy 'succeed' while prod stays broken, then verifies the live revision instead of trusting deploy output.
Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests.
Use Tree Ring Memory for local-first AI-agent memory lifecycle work: recall, evidence, audit, forgetting, and consolidation without transcript dumping.
Go in depth harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.