> ## Documentation Index
> Fetch the complete documentation index at: https://rllm-org-rllm-19-feat-renderer-parser-backend.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# rLLM CLI

> Evaluate, train, and monitor agents from the command line and web dashboard

rLLM provides two interfaces for working with agents: a **CLI** for running evaluations and training from the terminal, and a **web UI** for monitoring runs and exploring results.

## CLI

<Frame caption="The rLLM CLI help screen">
  <img src="https://mintcdn.com/rllm-org-rllm-19-feat-renderer-parser-backend/7-E2UzJlU3MmRZjg/assets/rllm-cli.png?fit=max&auto=format&n=7-E2UzJlU3MmRZjg&q=85&s=b8710e1f7e0be11f044b39256b93510a" alt="rLLM CLI showing the banner, available commands including agent, dataset, eval, init, login, model, and train, along with global options" width="1056" height="914" data-path="assets/rllm-cli.png" />
</Frame>

The `rllm` CLI is the primary way to evaluate and train agents. Datasets are auto-pulled from HuggingFace, agents and evaluators are resolved from the built-in catalog, and a local LiteLLM proxy handles API routing.

### First-time setup

Configure your model provider before running evaluations or training:

```bash theme={null}
rllm model setup
```

This walks you through selecting a provider (OpenAI, Anthropic, etc.), entering your API key, and choosing a default model. Configuration is saved to `~/.rllm/config.json`.

### Core commands

```bash theme={null}
rllm eval gsm8k                          # Evaluate on a benchmark
rllm train gsm8k --model Qwen/Qwen3-8B  # Train with RL
rllm init my-agent                       # Scaffold a new agent project
rllm dataset list --all                  # Browse available datasets
rllm model setup                         # Configure model providers
```

### Typical workflow

<Steps>
  <Step title="Configure your model">
    ```bash theme={null}
    rllm model setup
    ```
  </Step>

  <Step title="Explore available datasets">
    ```bash theme={null}
    rllm dataset list --all
    ```
  </Step>

  <Step title="Evaluate on a benchmark">
    ```bash theme={null}
    rllm eval gsm8k
    ```
  </Step>

  <Step title="Train with RL">
    ```bash theme={null}
    rllm train gsm8k --model Qwen/Qwen3-8B
    ```
  </Step>
</Steps>

### Global behavior

* **Auto-pull**: Datasets are automatically downloaded from HuggingFace when first referenced by `eval` or `train`.
* **LiteLLM proxy**: When no `--base-url` is provided, `eval` and `train` start a local LiteLLM proxy automatically, routing requests to your configured provider.
* **Lazy loading**: Commands are loaded on-demand, so `rllm --help` starts instantly regardless of installed extras.

## Web UI

The rLLM web UI at `ui.rllm-project.com` provides a dashboard for monitoring training runs and exploring evaluation results.

### Logging in

Authenticate with the hosted UI from the CLI:

```bash theme={null}
rllm login
```

This opens a browser for authentication and stores your API key locally in `~/.rllm/config.json`. You can also set the `RLLM_API_KEY` environment variable directly.

### Enabling UI logging

Add the `--ui` flag to `eval` or `train` to stream live data to the dashboard:

```bash theme={null}
rllm eval gsm8k --ui
rllm train gsm8k --model Qwen/Qwen3-8B --ui
```

When enabled, the CLI sends metrics, episode data, and step-by-step execution traces to the UI backend in real time.

### What you can see

The UI provides:

* **Episode explorer**: Browse individual episodes with full trajectory and step-level detail
* **Metrics dashboard**: Track rewards, success rates, and custom signals across training runs
* **Trajectory viewer**: Inspect agent reasoning chains and tool calls step by step

<Info>
  To use a self-hosted UI instance, set the `RLLM_UI_URL` environment variable to your instance URL.
</Info>