Skip to Content
ExamplesGive an agent a machine

πŸ’» Give an agent a machine to work on

Stack β€” Runner: any machine (laptop, build server, VPC box) Β· Connection: outbound only Β· Surface: commands + installed runtimes + filesystem Β· Output: work done on that box

Who it’s for β€” anyone whose agent needs to reach something a hosted agent can’t: internal services, on-prem data, private infrastructure. What it does β€” a small runner process you install on any machine gives agents a place to execute β€” run commands, use the runtimes already installed, touch that box’s files and network. Code, data, and credentials stay put; only instructions cross the wire.

Build it

  1. Install and start it on the machine:

    npx @almyty/auth login npx @almyty/runner start --name build-server

    It connects out (no inbound ports) and starts heartbeating.

    The Runners list β€” a machine online

  2. It reports what it can do. Open the runner and it shows the runtimes and tools it detected β€” Node, Python, Docker, Git β€” so an agent knows what’s available.

    A runner's detail β€” detected runtimes on the machine

  3. Point an agent at it. The agent executes on that machine as a step: run a test suite, query a DB only reachable inside the network, or process files that can’t leave.

Make it yours

  • Driving coding-agent CLIs is one capability built on this β€” not the point of the runner.
  • Reach a database that only listens on localhost inside a private subnet.
  • Keep regulated data on-prem while the control plane stays hosted β€” or self-host all of it.

Uses β€” Platform Β· Runner Β· On-prem