> ## Documentation Index
> Fetch the complete documentation index at: https://docs.stateset.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Agents CLI

> Every stateset-agents command, grouped by what it does — and which ones spend money.

One entry point, `stateset-agents`, installed with the package. Commands below
are grouped by the part of the loop they belong to.

```bash theme={null}
stateset-agents --help
stateset-agents version
```

## The improvement loop

| Command          | Does                                                                       |
| ---------------- | -------------------------------------------------------------------------- |
| `ingest`         | Convert OpenAI or LangChain logs into per-conversation transcripts         |
| `improve run`    | Grade, curate above a threshold, write `curated.jsonl` and `next_steps.md` |
| `improve status` | Read back a previous run's summary                                         |
| `evaluate`       | Score a model against a reward and a prompt set                            |
| `benchmark`      | Run the packaged benchmark suites                                          |

## Training

| Command        | Does                                    | Spends                          |
| -------------- | --------------------------------------- | ------------------------------- |
| `train`        | Train locally against a pinned backend  | Your own GPU                    |
| `train-remote` | Rent a GPU, train, evaluate, release it | **Yes — bound by `--max-cost`** |
| `chat`         | Talk to a local model or adapter        | No                              |
| `chat-remote`  | Talk to a remotely hosted adapter       | **Yes, while the pod is up**    |
| `undeploy`     | Tear down a deployment                  | No                              |

<Warning>
  `train-remote` and `chat-remote` rent hardware. `train-remote` refuses to
  start a run that could exceed `--max-cost` and terminates the pod on every
  exit path, including your machine dying mid-run. `chat-remote` holds a pod
  open for as long as the session lasts — close it when you are done rather
  than leaving a chat window open overnight.
</Warning>

## Setup and diagnosis

| Command           | Does                                                     |
| ----------------- | -------------------------------------------------------- |
| `init`            | Scaffold a project                                       |
| `doctor`          | Check the environment for the things that break training |
| `validate-config` | Check a config without running anything                  |
| `preflight`       | The checks `train` runs before it starts, on their own   |
| `publish-check`   | Verify a build is publishable                            |
| `provider-canary` | Prove a remote provider is reachable and behaving        |

<Tip>
  Run `doctor` before your first `train`, not after it fails. It catches the
  environment problems — driver, toolkit, disk, backend version — that otherwise
  surface an hour into a run as something that reads like a model problem.
</Tip>

## Model presets

Named presets resolve a model id with its hyperparameters, so a training command
does not carry twelve flags:

```bash theme={null}
stateset-agents qwen3-8-27b --help
```

Presets ship for the Qwen 3 family, Kimi K2.6 and K3, Muse Glimmer, Nemotron
3.5, Qwen 3 Coder, GPT-OSS and DeepSeek V4. `list_model_presets` in the
[MCP server](/stateset-agents/mcp-server) returns the same list with each
preset's key fields.

## Serving and integration

| Command    | Does                                              |
| ---------- | ------------------------------------------------- |
| `serve`    | Serve a trained model behind an API               |
| `mcp`      | Run the [MCP server](/stateset-agents/mcp-server) |
| `flywheel` | Drive the continuous improvement loop             |
| `advanced` | Lower-level entry points for the RL algorithms    |
| `research` | The auto-research workflows                       |

## Next steps

<CardGroup cols={2}>
  <Card title="Agents quickstart" icon="rocket" href="/stateset-agents/quickstart">
    These commands in the order you would actually run them.
  </Card>

  <Card title="Overview" icon="diagram-project" href="/stateset-agents/overview">
    The loop, the rewards and the backend adapters.
  </Card>

  <Card title="MCP server" icon="plug" href="/stateset-agents/mcp-server">
    Driving the loop from an agent.
  </Card>

  <Card title="RL platform" icon="brain" href="/guides/reinforcement-learning-platform">
    Where this sits in the wider StateSet RL story.
  </Card>
</CardGroup>