{
  "name": "LocalAGI",
  "slug": "localagi",
  "categories": [
    20
  ],
  "date_created": "2026-03-03",
  "type": "ct",
  "updateable": true,
  "privileged": false,
  "interface_port": 3000,
  "documentation": "https://github.com/mudler/LocalAGI#installation-options",
  "website": "https://github.com/mudler/LocalAGI",
  "logo": "https://cdn.jsdelivr.net/gh/selfhst/icons@main/webp/localagi.webp",
  "config_path": "/opt/localagi/.env",
  "description": "LocalAGI is a self-hostable AI agent platform with a web UI, OpenAI-compatible APIs, and local-first model orchestration.",
  "install_methods": [
    {
      "type": "default",
      "script": "ct/localagi.sh",
      "resources": {
        "cpu": 2,
        "ram": 4096,
        "hdd": 20,
        "os": "Debian",
        "version": "13"
      }
    }
  ],
  "default_credentials": {
    "username": null,
    "password": null
  },
  "notes": [
    {
      "text": "This script builds LocalAGI from source (Go + Bun) and runs it as a systemd service.",
      "type": "info"
    },
    {
      "text": "This Proxmox script runs LocalAGI in external-backend mode and does not provision local ROCm/NVIDIA runtimes.",
      "type": "info"
    },
    {
      "text": "By default, LocalAGI is configured to call an OpenAI-compatible backend at `http://127.0.0.1:11434/v1` (Ollama-compatible) via `LOCALAGI_LLM_API_URL`.",
      "type": "info"
    },
    {
      "text": "To use an external Ollama host, edit `/opt/localagi/.env` and set `LOCALAGI_LLM_API_URL=http://<ollama-host>:11434/v1`, then restart LocalAGI with `systemctl restart localagi`.",
      "type": "info"
    }
  ]
}