Post

LocalAGI

LocalAGI is a self-hostable AI agent platform with a web UI, OpenAI-compatible APIs, and local-first model orchestration.

LocalAGI
In Development
This script is currently in active development and may be unstable or incomplete. Use in production environments is not recommended.

Installation

Default install:

1
bash -c "$(wget -qLO - https://github.com/community-scripts/ProxmoxVED/raw/main/ct/localagi.sh)"
CPU: 2 cores RAM: 4096 MB Disk: 20 GB OS: Debian 13

Configuration

Config file:

1
/opt/localagi/.env

Notes

This script builds LocalAGI from source (Go + Bun) and runs it as a systemd service.
This Proxmox script runs LocalAGI in external-backend mode and does not provision local ROCm/NVIDIA runtimes.
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.
To use an external Ollama host, edit /opt/localagi/.env and set LOCALAGI_LLM_API_URL=http://:11434/v1</code>, then restart LocalAGI with systemctl restart localagi.</div> </div> ## Web Interface
Port: 3000
## Links - [Official Website](https://github.com/mudler/LocalAGI) - [Documentation](https://github.com/mudler/LocalAGI#installation-options) ---
This post is licensed under CC BY 4.0 by the author.