Getting Started

A small language model framework for local inference and fine-tuning.

Best Performance

For best performance, use an Apple Silicon Mac.

Installation

Homebrew (Recommended)

If you don't have Homebrew installed, install it first:

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

Then install Smartloop:

brew tap smartloop-ai/smartloop
brew install smartloop

Upgrade via Homebrew

brew update && brew upgrade smartloop

Quick Install (macOS / Linux)

Alternatively, use the following curl command to install the framework. It will install the service, update the config and configure the TUI:

curl -fsSL https://smartloop.ai/install | bash

Uninstall

# If installed via curl
curl -fsSL https://smartloop.ai/uninstall | bash

# If installed via Homebrew
brew uninstall smartloop
brew untap smartloop-ai/smartloop

Configuration

Initialize a new project with your developer token:

slp init -t <developer_token>

You can obtain your access token from https://app.smartloop.ai/developer. For more on token storage, CLI/TUI token commands, and how credentials are secured, see the Credentials page.

Usage

# View available commands
slp --help

Project Management

slp projects create <name>
slp projects list
slp projects switch <name>
slp status

Add a Document

Upload a document for training:

slp add document.pdf

Prompting

Start the interactive chat:

slp run

For a non-TUI experience:

slp run --no-tui

Server Management

SLP includes a background API server compatible with OpenAI's chat completion format.

slp server start
slp server stop
slp server status

On macOS (Homebrew):

brew services start smartloop
brew services stop smartloop

On Linux/WSL (systemd user service):

systemctl --user start smartloop
systemctl --user stop smartloop
systemctl --user status smartloop

Requirements

Requirement	Details
Platform	macOS (Apple Silicon) or Linux (x86_64)
Python	3.11 or later (installed automatically)
CMake	Installed automatically via Homebrew