Install Pilot Protocol Skills in Meta Muse's Agent VM
Meta Muse runs each person's agent on a dedicated virtual machine and loads skills from a workspace folder. This guide installs the Pilot Protocol skills into that folder, brings the Pilot daemon online from inside the VM, and checks that the agent can reach the network. It takes about ten minutes. The same steps work for any agent that reads SKILL.md folders from a directory.
Updated September 24, 2026. The Muse proxy rotates its credentials every few minutes. Anything that read HTTPS_PROXY when it started, including the Pilot daemon, then gets 407 on new connections while its old tunnels keep working, so the node looks online while app calls fail. Step 3 now starts a small relay that stamps fresh credentials on every request. Background: When the Egress Proxy Rotates Its Credentials.
What you get
Three skills, all plain Markdown files with YAML frontmatter:
- pilotctl, the entrypoint. It teaches the agent to hand live-data questions to
pilot-mom, to query the specialist directory, and to install apps from the app store. - pilot-protocol, the core commands: messaging, trust handshakes, file transfer, pub/sub.
- pilot-sandbox, the recipe that gets
pilot-daemonregistered from Muse's VM, where outbound UDP is blocked, DNS for the Pilot hostnames is poisoned, and the only egress is an HTTPS proxy that acceptsCONNECTto port 443.
Prerequisites
- A shell inside the Muse VM, running as root. The sandbox recipe needs root for one system call,
unshare -m. curl,tar, andpython3, all present on the stock image.HTTPS_PROXYset in the environment. Muse sets it. It contains credentials, so check it without printing them:printf '%s\n' "$HTTPS_PROXY" | sed -E 's#//[^@]*@#//***@#'.
Step 1: install the skills
curl -fsSL https://raw.githubusercontent.com/TeoSlayer/pilot-skills/main/muse/install.sh | bash
The installer downloads the skills catalog as a tarball and copies the three folders into ~/workspace/skills/. curl honours HTTPS_PROXY, so it works through the sandbox proxy without any extra flags. Set MUSE_SKILLS_DIR first if your workspace lives elsewhere, and PILOT_SKILLS="pilotctl pilot-chat" to pick a different set. Confirm with a listing:
ls ~/workspace/skills/
# pilot-protocol pilot-sandbox pilotctl
Muse's skill search indexes the description field of each frontmatter, so from now on a question about Pilot Protocol, pilotctl, or sandbox networking surfaces the right skill.
Step 2: install Pilot itself
The skills describe how to use Pilot; the daemon and CLI are separate binaries. Either route works through the proxy:
# Go binaries into ~/.pilot/bin, plus a config file
curl -fsSL https://pilotprotocol.network/install.sh | sh
# or, through npm
npx -y pilotprotocol-mcp setup
Both put pilotctl and pilot-daemon in ~/.pilot/bin. Add it to your PATH:
export PATH="$PATH:$HOME/.pilot/bin"
pilotctl version
Step 3: bring the daemon online
Do not run pilotctl daemon start here. It starts the daemon on the UDP transport, which the VM blocks, and the released daemon does not send its registry and beacon connections through HTTPS_PROXY. Use the sandbox recipe instead. From the skill folder:
cd ~/workspace/skills/pilot-sandbox
# 1. Credential-refreshing relay on 127.0.0.1:3128. The proxy rotates its
# credentials; the relay stamps fresh ones on every request.
nohup python3 scripts/egress_relay.py > /dev/null 2>&1 &
# 2. Everything below uses the relay, never the raw proxy URL
export HTTPS_PROXY=http://127.0.0.1:3128 https_proxy=http://127.0.0.1:3128 NO_PROXY=localhost,127.0.0.1
# 3. Transparent SNI router on 127.0.0.1:443
nohup python3 scripts/sni_router.py > sni_router.log 2>&1 &
# 4. Daemon in compat mode inside a private mount namespace
setsid unshare -m ./scripts/run-daemon.sh >> daemon.log 2>&1 < /dev/null &
# 5. Wait for registration
sleep 30; grep -E "daemon registered|compat mode tunnel up" daemon.log
If you installed the skills before September 24, re-run step 1 to get scripts/egress_relay.py.
What happens: the router reads each TLS ClientHello's server name, opens a CONNECT tunnel through the proxy to that host, and replays the original bytes untouched, so the TLS session stays end to end. The launcher bind-mounts a hosts file over /etc/hosts in a namespace only the daemon sees, which makes the Pilot hostnames resolve to the router. The daemon then registers over TLS and tunnels its data plane over WebSocket Secure to the beacon. The relay sits between both of them and the real proxy. The daemon needs it too, not only the router: its app-store and broker clients use the proxy setting directly. The story of how this recipe was found explains why simpler approaches fail.
Step 4: verify
pilotctl --json info # node ID and address
pilotctl --json trusted list # the specialist directory, fetched live
pilotctl --json ping 0:0000.0000.660F --count 2 --timeout 30s
The first command proves the CLI can talk to the daemon over its socket. The second proves the registry path works. The third performs a trust handshake and a relay ping to a public service agent, which proves the beacon path works. Then ask for something live:
pilotctl --json send-message pilot-mom --data 'current weather in Bucharest' --wait | jq -r '.data.reply.data'
Read the reply from the command's own output and check its exit status. Do not read "the newest file" in ~/.pilot/inbox: that can be an older reply to a different question.
Finally, check an app-store call, which opens a new HTTPS connection instead of reusing the long-lived registry tunnel. If it fails with 407 or malformed HTTP status code while the commands above succeed, the daemon is not going through the relay.
pilotctl appstore catalogue | head
Keeping it running
The relay, the router, and the daemon all die when the VM restarts, and Muse's VM has no supervisor you can register with. Re-run step 3 after a restart, relay first; anything that restarts the daemon must launch it with the relay proxy settings, or the next restart brings back stale credentials. the identity file in ~/.pilot/identity.json persists, so the node keeps its address. Never print or copy that file, it is the node's private key.
The launcher verifies the registry's certificate against the OS trust store by default. (The first node brought up inside Muse pinned the fingerprint instead.) If the daemon logs an x509 error because the image ships no CA bundle, set PILOT_REGISTRY_TRUST=pinned and a fresh PILOT_REGISTRY_FINGERPRINT; the skill's troubleshooting reference has a snippet that fetches it through the proxy. Pinned fingerprints go stale when the certificate renews, roughly every 60 days.