# Hosted Quickstart

Validate the CLI against the hosted production backend, set a workspace, and get to your first runnable command in a few minutes.

Source: https://www.agentclash.dev/docs/getting-started/quickstart
Markdown export: https://www.agentclash.dev/md/docs/getting-started/quickstart

This path is for people changing the CLI or trying the product without booting the whole stack locally.

The hosted backend needs an AgentClash account. If you do not have one yet, [sign up free](/auth/login?mode=signup) — the CLI login in step 2 uses the same account.

> Note: You do not need a seeded workspace to finish this. If yours has no challenge
> packs yet, author your first one in step 4 with `challenge-pack init`.
> `eval start` also needs an agent deployment, which you set up once in the web
> app — until then, stop after `challenge-pack publish`; you have still
> verified auth, connectivity, and workspace selection.

## 1. Install the CLI

```bash
npm i -g agentclash
```

## 2. Point the CLI at production and log in

```bash
export AGENTCLASH_API_URL="https://api.agentclash.dev"
agentclash auth login --device
```

Use `--device` when you are in a remote shell or do not want the CLI to open a browser automatically.

## 3. Link a workspace

```bash
agentclash link
```

The CLI resolves the API base URL in this order:

```text
--api-url > AGENTCLASH_API_URL > saved user config > built-in default
```

The built-in default depends on how the CLI was built: released binaries (what `npm i -g agentclash` installs) default to `https://api.agentclash.dev`, while source builds (`go run .` / `make build`) default to `http://localhost:8080`. Because this quickstart uses the released npm binary, you only need the `AGENTCLASH_API_URL` export above if you want to override that default.

`agentclash link` saves the selected workspace in user config so later commands do not need raw IDs by default.

## 4. Choose your next path

```bash
agentclash doctor
agentclash eval start --help
```

If the workspace is already seeded with challenge packs and agent deployments, create and follow a run:

```bash
agentclash eval start --follow
```

If the workspace is empty, scaffold a starter pack first:

```bash
agentclash challenge-pack init support-eval.yaml
agentclash challenge-pack validate support-eval.yaml
agentclash challenge-pack publish support-eval.yaml
agentclash eval start --follow
agentclash baseline set
agentclash eval scorecard
```

The last three commands also need an agent deployment, which the CLI does not scaffold. A deployment sits on top of an agent build with a ready build version, and you create both in the web app under **Builds**, then wire up the deployment under **Deployments** (see [Agents and Deployments](https://www.agentclash.dev/md/docs/concepts/agents-and-deployments) for the model, and [Configure Runtime Resources](https://www.agentclash.dev/md/docs/guides/configure-runtime-resources) for the CLI equivalent, which assumes the build already exists). Until a deployment exists, stop after `challenge-pack publish`: `eval start` fails with `no deployments found in workspace`.

## Verification

You should now have:

- a valid CLI login
- a default workspace linked locally
- a working connection to the hosted API
- either a created run or enough context to see what the workspace is missing
- a clear next step: publish a challenge pack, start an eval, or save a baseline

## See also

- [Self-Host](https://www.agentclash.dev/md/docs/getting-started/self-host)
- [Runs and Evals](https://www.agentclash.dev/md/docs/concepts/runs-and-evals)
- [CLI Reference](https://www.agentclash.dev/md/docs/reference/cli)
- [Datasets overview](https://www.agentclash.dev/md/docs/guides/datasets-overview)
- [Multi-turn packs](https://www.agentclash.dev/md/docs/challenge-packs/multi-turn)