Homing Pigeon

Works with Muse, Grok, ChatGPT, Claude, Gemini, Copilot, etc.

Your cloud SI is smart, but it can't touch your computer. Homing Pigeon fixes that: tell your SI to complete a task and it will do it on your machine (Linux/macOS/FreeBSD/Windows). The results return so that your SI can iterate — run the tests, read the failure, fix, repeat. From your phone, so from anywhere.

Think "GitHub self-hosted runner, but the control plane is email." Python 3.9+, standard library only, no dependencies. (Email is just the first transport — the protocol doesn't care about the pipe. See TRANSPORTS.md.)

⚠️ USE AT YOUR OWN RISK. This tool hands full administrative control of the machine to whoever holds the shared secret. It reads email and executes what it finds — blindly, as a privileged user. Anyone who can produce a correctly-signed email owns the box: install software, read files, add users, pivot to your network. Only run this with a dedicated throwaway account on a machine you can afford to lose, and read PROTOCOL.md before you deploy it.

What this is for

Homing Pigeon is a personal remote-development agent. The point is not that the SI becomes smarter. It is that the SI gets a way to delegate work to a computer it could not otherwise reach. The most powerful computer you have access to should not stop being useful the moment you walk away from your desk, and neither should your SI assistant.

Concrete uses:

• Remote test runs. Ask your SI to run the suite, read the failures, patch the code, rerun, and report back, all while you are away from the machine.
• Your hardware as a worker. Long builds, data crunching, batch jobs, on the workstation you own, without a remote-desktop session open.
• Scheduled-style automation. Maintenance scripts, reports, and repetitive technical tasks, dispatched from your phone.
• Cloud SI, local resources. Your files, your dev environment, your GPU, reachable by an assistant that lives in the cloud.
• Physical peripherals. Plug a sensor or servo board into a Raspberry Pi, point your SI at it, and let it write the control code and debug the hardware into motion. You do the soldering, it does the head-scratching. Let SI build a robot.

Send a job from your phone, let the big machine run the tests, crunch the data, or grind through the refactor, and read the results when they land in your inbox.

The SI systems are brilliant, but they are kept fenced off from our real machines. So instead we will point one at a disposable box, give it a signed channel, and let it do tasks from start to finish. The upside is an assistant that operates, not just advises. If the capability is real, there is very little downside to exercising it.

A new model claims to be good at something — robotics, automation, data work? Point it at a box and find out. The clock check in the RUNBOOK is the hello world; the ceiling is wherever your hardware goes. See Job 7.

It belongs to the same family as GitHub self-hosted runners, VS Code Remote tunnels, and Tailscale — legitimate tools for administering your own hardware remotely. And like all of those, its power is the point, not an accident: whoever holds the shared secret has full control of the machine. That's exactly why this project states its threat model plainly instead of burying it. Keep the secret like a password, use a throwaway account, and only ever install the agent on machines you own and operate.

  SI (cloud)                        Your machine
  ────────────                      ──────────────────
  send_job.py ──sign──▶ job email ──▶  runner.py
       │                  │              │  poll IMAP
       │                  │              │  verify HMAC
       │                  │              ▼
       │                  │           run script
       │                  │              │
       │               result email ◀──┘ sign
       ▼                  │
  verify result ◀──────────┘

Large inputs don't go through email: your SI uploads them to file hosting and the job email carries download URLs (with optional SHA-384).

Why email? Because it's the only transport with all five properties on day one: reachable from anywhere, outbound-only polling (no inbound ports — NAT-proof), at-least-once delivery, and zero infrastructure to operate. And because the protocol doesn't care about the pipe: Cloudflare Queues, NATS, MQTT, Redis Streams and friends all satisfy the same contract. Email is just Transport #1 — see TRANSPORTS.md.

Runbooks, not prompts. The SI doesn't chat about the task — it ships a runbook: deterministic steps, each with a check that proves the step worked. The runner executes it and reports back what actually happened, and that feedback goes into the next runbook. Each cycle is a little smarter than the last, because the failures are data. If you've ever debugged something by running it, reading the output, and trying again with what you learned — that's the whole product. The SI is just the part that writes the next attempt.

The Oracle: answers, not output

v1 sends full job output back to the SI. v3 flips this: your machine becomes the Oracle — a black box the SI can question but never inspect.

The SI asks "did the tests pass?" or "does the output contain secrets?" and gets back HMAC-signed attestations: proofs about the output that reveal nothing else. It's the zero-knowledge shape applied at the trust boundary — prove things about your data without showing your data. The raw output never leaves your disk.

  Cloud SI                                Your machine
  ────────                                ────────────────────
  "Did the tests pass?" ──signed──────▶ ┌─────────────┐
                                        │  The Oracle │
  "Any secrets in there?" ────────────▶ │             │
                                        │ output stays│
   ┌─────────────────────┐             │ on your disk│
   │ signed attestation   │ ◀──signed── │             │
   │ { exit_zero: true,   │             │ answers only│
   │   no_secrets: true } │             │ what policy │
   └─────────────────────┘             │ allows      │
                                        └────────────┘
   The SI learns answers. Never the raw output.

Queries are declared upfront (no adaptive probing), each job gets a privacy budget bounding total leakage, and the disclosure ceiling is set by you in config — never by the SI. For debugging, oracle_enabled: false drops back to the plain v1 pipe.

The Oracle also grows two optional capabilities (spec'd, not yet built):

• Local inference. Point it at a model running on your own box and the SI can ask questions in plain English — "why did the tests fail?" — answered locally, with only the answer crossing the boundary. The endpoint must be loopback (fail closed), and every answer is truncated, redacted, and secret-scanned before it's sent. The SI gets useful answers, and your raw data never leaves the machine.
• Execution confinement. Tell the Oracle the one folder jobs may touch (workspace_root) and it attests the job stayed inside — confined_to_workspace, signed like everything else. Today's enforcement is attested; OS-level sandboxing is the stronger future.

Full spec in PROTOCOL.md (sections 9–12).

Layout

• PROTOCOL.md — the full wire protocol (message formats, signatures, verification rules, security model).
• TRANSPORTS.md — email is just Transport #1. Alternatives that satisfy the transport contract: Cloudflare Queues (the pick), NATS, MQTT, Redis Streams, Postgres, Durable Objects.
• SAFEGUARDS.md — how to run this without getting burned: the non-negotiables, containment, the Oracle as a safeguard, and what to do when something goes wrong.
• runner/runner.py — the agent. Polls IMAP, verifies, executes, replies via SMTP. No dependencies beyond Python 3.9 stdlib.
• runner/install.py — installs it as a boot-start service: systemd (Linux), launchd (macOS), cron @reboot (FreeBSD), Scheduled Task (Windows).
• runner/config.example.json — copy to config.json and fill in.
• cloud/send_job.py — cloud-side helper: builds signed job emails, verifies result emails. (Your SI uses this logic when dispatching jobs.)
• tests/test_runner.py — end-to-end tests with fake IMAP/SMTP servers.
• RUNBOOK.md — step-by-step instructions (written for a 5-year-old): cloning, pushing, cutting a release, installing, sending a job.
• examples/hello-world.json — unsigned example job payload.

Setup

By default the installer also sets up local inference for the Oracle ask op: it installs Ollama (if missing) and pulls a model (llama3.2:3b by default). Pass --no-inference to skip that. The runner itself never bundles the model; Ollama runs separately on loopback.

Easiest: download a release. No Python needed — each release ships standalone binaries built by GitHub Actions:

The Linux binary is built on ubuntu-22.04 (glibc ~2.35). It runs on Ubuntu 22.04+, recent Debian, and most current distros. We don't ship binaries for older systems (Debian 11, Ubuntu 20.04, RHEL 8) because of their older glibc, but the runner itself is stdlib-only Python and runs fine there: use pip install pigeon-home-runner or build from source.

1. Extract the archive on the target machine.
2. Run install (or install.exe on Windows). It copies the runner binary, writes a default config.json, and registers the boot-start service (systemd / launchd / cron @reboot / Scheduled Task).
3. Edit config.json. Two ways to sign in:
   • Password (default): mailbox_user + mailbox_password (Gmail app password, plaintext, on purpose). The HMAC shared secret is a separate shared_secret value — generate one with openssl rand -hex 32.
   • Browser, like Thunderbird: no Google password anywhere. Create a Desktop OAuth client in Google Cloud Console (APIs & Services → Credentials → Create OAuth client ID → Desktop app), then in config.json set "auth": "oauth", put the client id in oauth_client_id (and oauth_client_secret if Google gave you one), and set shared_secret to a random string — that's the HMAC key your SI uses to sign jobs. Then run homing-pigeon-auth (or python runner/oauth.py --config config.json from source): a browser opens, you sign in and grant access, and the refresh token is stored. IMAP and SMTP then use XOAUTH2. Tested end to end on Windows 11. (your explicit choice for this throwaway account).
4. When you want an SI to send jobs, generate a shared secret (openssl rand -hex 32), put it in shared_secret in config.json, and paste the same string to the SI in chat.

From Docker — the fastest path, no Python or git needed:

docker run -d --name pigeon --restart unless-stopped \
  -e PIGEON_MAILBOX_USER="your-runner@gmail.com" \
  -e PIGEON_MAILBOX_PASSWORD="your-app-password" \
  -v pigeon-data:/data \
  ghcr.io/pigeon-home/homing-pigeon:latest

See DOCKER.md for the full guide — dry-run mode, config file mounting, updating, and security notes.

From PyPI (needs Python 3.9+) — the easiest path on machines where Python is preinstalled, like a Raspberry Pi. A Pi is the ideal box for this: always on, sips power, and a machine you can afford to lose — which is this project's whole security posture:

pip install pigeon-home-runner

This installs three commands: homing-pigeon, homing-pigeon-install, and homing-pigeon-send-job (the cloud-side helper). Then:

1. homing-pigeon-install copies the runner, writes a default config.json, and registers the boot-start service.
2. Edit config.json and share the app-password string with your SI, same as above.

From the release files (same Python requirement): each GitHub release also ships an sdist (.tar.gz) and a universal wheel (.whl), plus standalone binaries (below) and a SHA384SUMS file so you can verify your download:

1. Download the .whl from the release.
2. pip install pigeon_home_runner-*-py3-none-any.whl — same three commands as above.
3. homing-pigeon-install copies the runner, writes a default config.json, and registers the boot-start service.
4. Edit config.json and share the app-password string with your SI, same as above.

From source (needs Python 3.9+):

1. Create a dedicated Gmail account for the runner, e.g. myname-runner@gmail.com. Never use a personal inbox.
2. Enable 2-Step Verification, then create an app password (Google Account → Security → 2-Step Verification → App passwords).
3. Copy runner/ to the target machine.
4. Copy config.example.json to config.json and fill in mailbox_user and mailbox_password as above.
5. Test one cycle: python3 runner.py --config config.json --once.
6. python3 install.py registers the boot-start service for your platform (see below).

Per-platform install

install.py --dir DIR chooses the install location (default ~/.homing-pigeon); install.py --uninstall removes the service.

Run it in a VM

For testing — and honestly for everyday use — run the agent inside a Linux VM on your own hardware rather than directly on the host:

• Snapshots beat regret. About to hand an SI the keys to a machine? Snapshot first. If a job goes sideways, roll back in seconds.
• Containment. The agent only sees what the VM sees. Your host, your files, and your other projects stay out of reach of anything a job does.
• Disposability. Experiment freely: spin up a fresh VM for a new idea, tear it down when you're done. Nothing lingers on the host.

Any hypervisor works — KVM/QEMU, VirtualBox, Hyper-V, VMware. Give the VM internet access (NAT is fine) so it can reach Gmail's IMAP/SMTP, install the Linux release binary inside the guest, and point your jobs at it. The host never needs to know.

How scripts run

Jobs carry a script (or script_url) plus an optional interpreter list, e.g. ["bash"] or ["pwsh", "-File"]. The runner writes the script to the job's work dir and runs <interpreter...> script <args...>. Defaults: PowerShell on Windows, sh elsewhere; override per-install with default_interpreter in config.json, per-job with interpreter in the job (send_job.py new --interpreter '["bash"]').

Sending a job (any SI)

The runner is SI-agnostic: anything that can send email as the runner's Gmail account and sign the body can drive it — your SI of choice, a cron script, whatever. The SI needs the shared secret string from step 5 (which is the app password itself, your choice). Then:

python3 cloud/send_job.py new --kind ping --secret <the-string>
# prints: subject line, blank line, signed body -> send as email to the runner mailbox

python3 cloud/send_job.py new --kind exec --script-file job.sh \
  --interpreter '["bash"]' --file data.csv=https://... --timeout 300 \
  --secret <the-string>

Or just paste the string to your SI in chat — it composes, signs, and sends the job email itself, and reads the result email when it arrives. Large files are uploaded to cloud storage first; the job email carries the URLs.

Verify a result body:

python3 cloud/send_job.py verify --secret <the-string> result.txt

Testing

Watch before you trust. The runner is fully inspectable — these flags exist so you can audit everything it would do before it does it:

python3 runner/runner.py --config config.json --once --dry-run --verbose
# verifies signatures, prints what each job WOULD do, executes nothing,
# sends nothing, changes nothing (mail stays unseen)

install.py accepts the same flags and bakes them into the installed service, so the agent on boot runs exactly what you tested: python3 runner/install.py --verbose --poll-interval 30.

python3 -m pytest tests/   # or: python3 tests/test_runner.py

The suite drives the real runner code against fake IMAP/SMTP servers: ping roundtrip, script execution, timeout kill, poison-job rejection, signature/tamper rejection, any-sender acceptance.

End-to-end without your SI:

1. python3 cloud/send_job.py new --kind ping --secret <the-string> → copy the subject + body.
2. From any email account, send it to the runner mailbox.
3. On the target machine: python3 runner.py --config config.json --once.
4. A result email with stdout: "pong" should arrive in the mailbox.

Security notes

• The runner is a full-trust execution environment: a valid signed job email means arbitrary code as a privileged user. The app password sits in plaintext in config.json (your explicit choice: throwaway account, fresh box). Anyone holding it gets Gmail access. The HMAC shared secret is a separate value — anyone holding it can sign jobs. Don't use this setup with an account you care about.
• Every job is HMAC-SHA-384 signed; the signature is the sole authentication gate. Timestamp window and replay protection (seen-set) are enforced before anything runs; the sender address is logged but never trusted.
• Delivery is at-least-once: if a result email fails to send, the job stays unseen and will be re-executed next cycle. Make jobs idempotent or check the seen behavior accordingly.
• Hardening ideas still open: encrypted credentials at rest, per-job encryption, result file upload for large outputs. The Oracle is implemented: result policies, signed attestations, and a query budget, so a cloud SI learns answers about your output without ever seeing it. oracle_enabled: false disables it anytime.

Roadmap

• v2 = who signs (shipped)
• v3 = what comes back — the Oracle: result policies, attestations, task dispatch, multi-secret, and the ask op (shipped as 3.0.0). The ask endpoint must be loopback or the op stays off.
• v4 = watch the Oracle think — the loopback dashboard (spec in ORACLE_DASHBOARD.md, not started)

Later:

• Cloudflare Queues as Transport #2
• Thunderbird-grade OAuth decision for future users

Status

v1.4.4. Grok hardened the config hot-reload: bad files don't poison retries, CLI flags can't be undone by later edits, and invalid values (negative intervals, non-numbers) are rejected instead of crashing the loop. v1.4.3. The runner now hot-reloads config.json — edit poll interval, workers, timeouts, or output limits and they take effect within one poll cycle, no restart needed. Includes Grok's doc fix dropping the last leftover "From hard rule" references. v1.4.1. Release binaries now carry Sigstore build provenance attestations — verifiable proof they were built by this repo's CI. v1.4.0. The sender address is no longer validated — any sender may submit jobs, and the HMAC signature is the sole authentication gate. The sender is logged for audit but never trusted. v1.3.1. PowerShell jobs stage as script.ps1 (Windows -File requires the extension — every exec job failed without it); dead OAuth refresh tokens now raise a distinct error and log once to the Windows Event Log instead of failing silently. v1.3.0: Thunderbird-style Google sign-in: the runner opens your browser, you sign in like adding Gmail on your phone, and IMAP/SMTP use XOAUTH2 from then on — no app password. Tested end to end on Windows 11: browser login, job sent, runner polled and executed it, result emailed back, all over OAuth. Password auth stays the default and is untouched. Runner rewritten in cross-platform Python; crypto tested (sign/verify roundtrip, tamper rejection, CRLF tolerance); end-to-end suite passes against fake mail servers (103 tests). Debug/audit flags (--dry-run, --verbose, --pdb, --no-send), concurrent job execution (--workers), SHA-384 release hashes, and PyPI distribution (pip install pigeon-home-runner). Releases ship standalone binaries (Windows/macOS/Linux) plus a Python wheel and sdist. The v3 protocol — the Oracle, privacy-preserving results via signed attestations — is spec'd in PROTOCOL.md and awaiting implementation.