Installation

1. Install fast-rlm

pip install fast-rlm

2. Install Deno

fast-rlm requires Deno 2+ as its runtime engine.

macOS / LinuxWindows

curl -fsSL https://deno.land/install.sh | sh

Then add Deno to your PATH:

export DENO_INSTALL="$HOME/.deno"
export PATH="$DENO_INSTALL/bin:$PATH"

irm https://deno.land/install.ps1 | iex

Or install via npm:

npm install -g deno

Verify the installation:

deno --version

3. Set your API key

fast-rlm uses OpenRouter by default. Set your API key:

export RLM_MODEL_API_KEY=sk-or-...

Tip

Add this to your .bashrc, .zshrc, or .envrc so it persists across sessions.

4. (Optional) Install Bun

Only needed if you want the interactive TUI log viewer (fast-rlm-log <file> --tui).

macOS / LinuxWindows

curl -fsSL https://bun.sh/install | bash

Then add Bun to your PATH (the installer will print the exact lines, but typically):

export BUN_INSTALL="$HOME/.bun"
export PATH="$BUN_INSTALL/bin:$PATH"

powershell -c "irm bun.sh/install.ps1 | iex"

Or install via npm:

npm install -g bun

Verify the installation:

bun --version

Tip

Add the PATH export to your .bashrc, .zshrc, or .envrc so bun is available in every new shell session.

Environment Variables

Variable	Description	Default
RLM_MODEL_API_KEY	API key for your LLM provider	(required)
RLM_MODEL_BASE_URL	OpenAI-compatible base URL	https://openrouter.ai/api/v1

You can point fast-rlm at any OpenAI-compatible API:

export RLM_MODEL_API_KEY=sk-...
export RLM_MODEL_BASE_URL=https://api.openai.com/v1