Pelorus

Pelorus is an AI navigator for Selkies-powered Linux desktops that gives a large language model (LLM) agent control over the mouse, keyboard, screenshots, and…

  • AI
  • Home Automation
Pelorus is an AI navigator for Selkies-powered Linux desktops that gives a large language model (LLM) agent control over the mouse, keyboard, screenshots, and window management. It runs a FastAPI server that connects the LLM (Ollama, OpenAI-compatible, or Gemini) to the desktop through the Pixelflux computer-use backend, the Linux accessibility tree (AT-SPI), and optional KWin D-Bus integration, so you can hand desktop tasks to an AI agent.

Platform availability

Available on 2 of 10 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

61/100 Good

Maintained
100last commit 12 days ago
Popular
123 GitHub stars
Easy to install
452 install platforms, install notes, Docker image
Light to run
No data

Based on 3 of 4 factors.

Availability: platform listings confirmed today, links checked 5 days ago

GitHub stars
3
Open issues
0
Last commit
2026-11-09
Latest release
0.2.4-ls20
License
GPL-3.0
Activity
steady

Checked 12 days ago - source: GitHub (linuxserver/docker-pelorus)

Resources & Compatibility

ARM (e.g. Raspberry Pi) is not supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Install the core Pelorus stack Run Helm (a tool for installing apps on Kubernetes) with: helm install pelorus charts/pelorus --namespace pelorus. This sets up the exporters, Prometheus, and Grafana needed to collect and display metrics. source
  • Check the Pelorus pods are healthy After install, run: oc get pods --namespace pelorus and look for Running or Completed pods. If they keep restarting, Pelorus may not collect metrics or show dashboards. source
  • Label apps so Pelorus can see deploys Add a Kubernetes label (a key-value tag used to find resources) app.kubernetes.io/name to the apps you want to monitor, like the mysql example. Without it, Pelorus may not match your deployments to the metrics. source

Fetched 39 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Which port does Pelorus listen on by default?

It listens on 0.0.0.0:5100 unless the PELORUS_PORT environment variable is set.

Where does Pelorus keep its server configuration?

It creates /config/agent/config.toml on first run, seeded from environment variables. The model servers are defined in that file.

Answers sourced from github.com

Community

Collected 53 days ago - public community threads