LlamaMan

A browser-based UI for launching, monitoring, and managing multiple llama.cpp server instances.

  • AI
  • Other
  • Tools & Utilities
A browser-based UI for launching, monitoring, and managing multiple llama.cpp server instances. Spawns llama-server as sibling Docker containers using official llama.cpp images. Includes an Ollama-compatible API proxy for use with Open WebUI. Universal GPU support for NVIDIA, AMD (ROCm), Intel Arc, and CPU. Auto-detects GPU vendor at startup. Optional multi-node clustering with shared database.

Platform availability

Available on 1 of 10 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • 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.

69/100 Good

Maintained
100last commit 18 days ago
Popular
2415 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
No data
Security check
95no serious findings, CI, tests

Based on 4 of 5 factors.

Availability: platform listings confirmed today, links checked 31 days ago

GitHub stars
15
Open issues
1
Last commit
2026-11-03
Latest release
2.2.61
Activity
declining

Checked 9 days ago - source: GitHub (nullata/llamaMan)

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

  • Create your admin account on first launch Open llamaMan's web page when it first starts and complete the setup form to create an admin account. If you skip this, you won't be able to sign in later. source
  • Set folders and open the web ports Start it with MODELS_DIR, DATA_DIR, and LOGS_DIR pointing to folders you can back up, then open port 5000 for the web UI/API and port 42069 for the Ollama-style proxy. Without those folders or ports, your settings can be hard to find and other apps or your browser may not be able to reach llamaMan. source
  • Create the database and set its password If you're using Docker, create the llamaman MySQL/MariaDB database and user, then set DATABASE_URL with the matching password. If the database or connection string is wrong, llamaMan can't save its data and will fail to start. source

Fetched 39 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Does llamaMan need llama.cpp or a GPU installed locally?

No, llamaMan itself has no llama.cpp code and no GPU dependency. It starts official llama.cpp server containers, and those containers can use CPU or a GPU.

How do I update the llama.cpp server without changing llamaMan?

Pull a newer official llama.cpp server image. The llamaMan UI does not need to be changed to update the underlying llama.cpp server.

Can llamaMan run outside of Docker?

Yes, it can run bare-metal on the host. In Docker mode it reaches sibling containers by container name, while bare-metal mode reaches spawned containers through localhost on their published ports.

Can I use llamaMan with Open WebUI?

Yes, it includes an Ollama-compatible API proxy. That lets it drop in as the backend for Open WebUI.

Answers sourced from github.com, github.com

Community

Collected 48 days ago - public community threads