Nixi portrait

Meet Nixi

Your AI-powered homelab assistant, built on NixOS. Manage servers, containers, and infrastructure through natural conversation. Bring your own LLM. Open source, always.

$ curl -sSL nixi.sh/install | bash click to copy Copied!

What can Nixi do?

Talk to your NixOS system like you talk to a colleague. Nixi handles the rest.

Bring Your Own LLM

Works with Ollama, LM Studio, llama.cpp, vLLM, or any OpenAI-compatible API. Your hardware, your models, your data.

NixOS Configuration

Edit configs, rebuild, rollback, manage services and generations - all through natural language.

Podman Containers

Deploy containers from GitHub or Docker Hub, manage stacks, parse compose files. GPU passthrough included.

Multi-Node Management

Manage multiple NixOS systems from a single controller via SSH. Adopt, configure, and monitor remote nodes.

Persistent Memory

SQLite-backed memory with full-text search. Nixi remembers context across conversations so you don't repeat yourself.

GPU Support

NVIDIA and AMD detection, driver management, ROCm/CUDA setup, and GPU passthrough to containers.

Network & Storage

DNS, firewall, port scanning, NFS/SMB/USB mounts - full network diagnostics and storage management.

Security-First

Confirmations for all mutations. Warnings for insecure requests. Scoped file access. You stay in control.

Scheduling & Logs

Create systemd timers, analyze journal logs by unit, priority, or time range. Automate and debug with ease.

NixOS

Why NixOS?

NixOS is the natural choice for an AI-managed server. Here's why it fits so well.

Declarative by design

Your entire system is defined in config files. An AI agent doesn't need to guess what state your server is in - it can just read the config and know exactly what's running, what's installed, and how everything fits together.

Atomic and reversible

Every change in NixOS creates a new generation. If an agent makes a mistake, you roll back in seconds. No half-applied updates, no broken state. Try doing that with apt or yum.

Reproducible everywhere

The same config produces the same system, every time. When Nixi manages multiple nodes, it can apply identical configurations across your fleet without worrying about drift or snowflake servers.

Safe to automate

Traditional package managers make permanent changes that are hard to undo. NixOS builds the new system alongside the old one and switches atomically. That makes it safe to let an agent handle rebuilds without babysitting.

Terminal & Web, Your Choice

Full-featured TUI for the terminal or a web interface you can access from any browser. Both with complete feature parity.

localhost:6494
Nixi Web UI screenshot

Get Started

Install Nixi in seconds. Choose the method that works best for you.

The fastest way to get started. Downloads and installs the latest release.

curl -sSL nixi.sh/install | bash

Clone the repository and build from source. Requires Go 1.26+.

git clone https://codeberg.org/ewrogers/nixi.git
cd nixi
go build -o nixi ./cmd/nixi

Add Nixi as a flake input for declarative NixOS installs.

# Add to your flake inputs
{
  inputs.nixi.url =
    "git+https://codeberg.org/ewrogers/nixi";
}

Supported platforms

Linux / x86_64 Linux / ARM64 Linux / RISC-V macOS / Apple Silicon macOS / Intel

Two Ways to Chat

Whether you prefer the terminal or a browser, Nixi has you covered.

Terminal UI

Rich TUI powered by Bubble Tea

./nixi

Slash commands work in both interfaces:

  • /help - list available commands
  • /model - switch LLM models
  • /system - show system info
  • /nodes - list managed nodes
  • /memories - browse saved memories

Web UI

Access from any browser on your network

./nixi serve

Then open your browser to:

http://localhost:6494

Full feature parity with the TUI: streaming responses, slash commands, confirmations, and multi-node support.

Ready to meet Nixi?

Free and open source under AGPL-3.0. Your system, your LLM, your rules.