hachiflow.com
self hosted

Your agents run on your machine.

Waggle's runner, runnerd, runs on a computer you already own or control. Each agent turn executes there, in a container, not on a server we operate. USD 20 a month, one account, every workspace you own.

Signing in costs nothing. The plan starts when you want agents of your own to run.
how it connects

Four steps, no server to run.

Everything starts in the builder at app.hachiflow.com/waggle.

01

Sign in

Open the builder and choose Self hosted. There is no separate sign up form.

02

Pick your platform

Download runnerd for macOS on Apple silicon, Linux x64 or Windows x64. All three need Docker running.

03

Run the command

The builder shows one command with your enrollment token already in it. Paste it into a terminal on that machine. On macOS and Linux it installs runnerd as a background service, no sudo needed on Linux, and it keeps running after you log out. On Windows it runs in that terminal for now.

04

Your machine comes online

The builder tells you the moment runnerd connects, and agents in your workspaces can start work.

platforms

One runner, three platforms.

runnerd is a single static binary, built for each platform straight from the same source. All three need Docker running.

macos

macOS on Apple silicon

Needs Docker Desktop running. The builder's command uses curl, which does not trigger Gatekeeper's quarantine block. If you download the binary in a browser instead, clear the quarantine flag first:

clear the quarantine flag
$ xattr -d com.apple.quarantine runnerd

The command installs runnerd as a background launchd service that starts at login and keeps running. Docker Desktop does not offer gVisor, so containers run with every capability dropped and no new privileges allowed instead.

linux

Linux x64

Needs Docker running. The command installs runnerd as a systemd service, no sudo required, in about 99 seconds end to end.

It stays online after you log out. gVisor is optional: when it is installed, runnerd uses it for every container automatically; without it, every container still runs with every capability dropped and no new privileges allowed.

windows

Windows x64

Needs Docker Desktop running, on the WSL2 or Hyper-V backend. The binary is not code signed yet, so Windows SmartScreen warns once: choose More info, then Run anyway.

There is no background service on Windows yet, so the command keeps runnerd running in that terminal; closing it stops your agents until you run it again.

the shape of the command
# the builder's copy has your real enrollment token in it, not a placeholder $ curl -fsSLo runnerd 'https://get.hachiflow.com/waggle/download/runnerd/<platform>' && chmod +x runnerd && ./runnerd install --control 'https://api.hachiflow.com' --enroll '<token>'
what actually happens

What leaves your machine, and what does not.

Short, checkable sentences, the same ones a security reviewer gets.

  • Each agent turn runs in a locked-down Docker container on your machine. On Linux, when gVisor is installed, the container runs under it; runnerd says which at startup. Without gVisor, on any platform, the container still runs with every capability dropped and no new privileges allowed.
  • Model requests go from your machine straight to the model provider, Anthropic for a Claude Code subscription or OpenAI for Codex, using the subscription you connect. We are not in that path, and we do not add a margin to it.
  • A small event for every run, started, done, or failed, is sent to hachiflow, so the builder can show your team what happened.
  • We hold the model credential you connect, a Claude Code subscription token or a ChatGPT sign-in through Codex, in our credential store, so your runner can use it. We do not claim otherwise.
  • Workspace chat and history are stored on our control plane, not on your machine. They are not end-to-end encrypted, and we can read them.
  • runnerd only ever connects out. You never open an inbound port for it.
  • runnerd updates itself. When a new version ships, it downloads it, verifies the checksum, and swaps it in; if the new version fails to come up cleanly, it rolls back to the one that was working, automatically.
  • Your machine's secret with hachiflow rotates on its own over the connection it already has open. There is nothing for you to rotate by hand.
  • Our control plane runs no agent code. It can wake an agent you already registered; it cannot execute anything on your machine beyond that.
price

USD 20 a month, per account.

One plan, no tiers. It covers every workspace this account owns.

Self hosted
$20/month

Your agents run on a computer you own. You keep it on; we connect it.

Start with Self hosted
  • Covers all your workspaces
  • Runner for macOS on Apple silicon, Linux x64 and Windows x64
  • One command to connect it, with your token already in it
  • Model use billed to your own Claude or ChatGPT subscription
  • Members you invite pay nothing to work with your agents

Prices do not include model use. Manage or cancel from the builder any time; a cancelled plan runs to the end of the month you paid for.

faq

Questions a developer asks first

Do I need Docker?

Yes, on all three platforms. Each turn runs inside a locked-down container; on Linux, gVisor sandboxes it further when it is installed.

What happens if my machine is off?

Agents in workspaces you own cannot run until it is back on and connected. Members you invite need no plan of their own, but they depend on your machine being up.

Does my data stay on my machine?

Execution does; workspace history does not. We store your workspace's chat and history on our control plane, and we can read it. Self hosted moves where agents run, not where conversations are kept.

Can I use a model other than Claude?

Yes. Waggle also runs OpenAI's Codex on the same self hosted runner: choose Codex when you make an agent and connect the ChatGPT plan or OpenAI API key you have instead of a Claude subscription. Model use is billed to whichever one you connect.

How is this different from Hosted by us?

Same builder, same model billing. Self hosted runs agents on hardware you control; Hosted by us runs them on a machine we rent and operate, for USD 49 to USD 129 a month depending on machine size.