# Configure Valdr
Valdr is installed and running. Now wire it up. This page walks through the three steps that turn a fresh install into a working agent operations platform: **install packs, register providers, and configure your first project.** Most of this takes under five minutes.

## What this page covers

- Installing Valdr packs (agents, prompts, capabilities)
- Registering AI providers and creating agent presets
- Setting up your first project

---

## 1. Install Valdr Packs

Valdr packs bundle agents, prompts, and capabilities into portable archives. The default pack ships with pre-built agents for orchestration, planning, execution, review, and auditing — so you're productive immediately.

### Download the latest packs

Official Valdr packs are published as releases on GitHub:

1. Go to [projectviking-ai/valdr-packs](https://github.com/projectviking-ai/valdr-packs)
2. Download the latest release archive

### Unpack into your repo

Unpack the archive into your local repository so packs travel with your codebase:

```bash
# From your repo root — recommended location
mkdir -p .valdr/valdr-packs
tar -xzf valdr-pack-*.tar.gz -C .valdr/valdr-packs/
```

Or place them in a top-level `valdr-packs/` directory in your repo:

```bash
mkdir -p valdr-packs
tar -xzf valdr-pack-*.tar.gz -C valdr-packs/
```

Valdr discovers packs in both locations. Keeping them in-repo means every collaborator gets the same agents, prompts, and capabilities when they clone.

### Where Valdr looks for packs

| Location | Scope | When to use |
|----------|-------|-------------|
| `./.valdr/valdr-packs/<pack>/` | Repo-local | Travels with the codebase in version control (recommended) |
| `./valdr-packs/<pack>/` | Repo-local | Alternative repo-local location |
| `~/.valdr/valdr-packs/<pack>/` | User-wide | Available across all your projects |

### What's in the pack

After unpacking, you'll have the full agent roster: orchestrators, planners, executors, reviewers, and auditors — plus shared prompts and capabilities. See the [Valdr Packs guide](/valdr/docs/valdr-packs/) for details on pack structure and authoring your own.

### Import via the UI

You can also import packs through the Valdr UI:

1. Open **Settings > Valdr Packs**
2. Click **Import Pack** and select the `.valdr-pack.tar.gz` archive
3. Review the preflight summary — it shows what will be added and flags any conflicts
4. Confirm the import

---

## 2. Register providers and create presets

Providers are the AI backends Valdr talks to — Claude, Codex, Ollama, and others. Presets are saved launch configurations that pair a provider with a model, runtime settings, and worktree policy. **You need at least one provider and one preset before you can launch agents.**

### Add a provider

1. Open **Settings > Providers**
2. Click **+** to add a new provider
3. Fill in the provider details:
   - **Display name** — what you'll see in dropdowns (e.g., "Claude Code")
   - **Type** — the integration protocol (`claude`, `codex`, `ollama`, etc.)
   - **Default model** — the model used when none is specified
   - **Models** — register the models available through this provider
4. Set **Enabled** to Yes
5. Save

### Set up environment variables

Some providers need API keys. Valdr never stores secrets directly — presets reference environment variable **names**, and values are loaded from your shell environment at launch time.

Export your keys in your shell profile (e.g., `~/.zshrc`):

```bash
# Add the keys for providers you use
export ANTHROPIC_API_KEY="sk-ant-..."
export CODEX_API_KEY="..."
export OPENAI_API_KEY="sk-..."
```

Reload your shell or source the file:

```bash
source ~/.zshrc
```

### Create an agent preset

1. Open **Settings > Agent Presets**
2. Click **+** to create a new preset
3. Configure:
   - **Key** — unique slug like `coder-claude` or `reviewer-codex`
   - **Provider** — select from your registered providers
   - **Model** — pick a model from that provider
   - **Env refs** — comma-separated variable names the agent needs (e.g., `ANTHROPIC_API_KEY`)
   - **Worktree options** — keep "Create worktree by default" checked for branch isolation and easier review
4. Save

You can create multiple presets for different workflows: a coding preset with a powerful model, a review preset with a faster one, a local Ollama preset for offline work. Switch between them per-launch without reconfiguring anything.

{{< callout type="tip" >}}
**Start with one preset and expand from there.** A single Claude or Codex coding preset is enough to run your first agent. Add review and orchestration presets as your workflow matures.
{{< /callout >}}

### Import presets from a provider pack

If your team has shared [Provider Packs](/valdr/docs/valdr-provider-packs/), you can skip manual setup entirely:

1. Go to **Settings > Providers** and click **Import**
2. Load the provider pack — providers, models, and defaults are created automatically
3. Go to **Settings > Agent Presets** and click **Import**
4. Load the preset pack — ready-to-use launch configurations appear instantly

This is the fastest path for teams: one person configures, everyone imports.

---

## 3. Set up your first project

Projects in Valdr organize tasks, sprints, and agent work under a single umbrella. You need at least one project before you can create tasks and launch agents against them.

1. Open **Projects** from the sidebar
2. Click **New Project**
3. Fill in:
   - **Name** — descriptive project name
   - **Key** — short, slug-friendly identifier used across the UI and MCP commands (e.g., `my-api`, `webapp-v2`)
   - **Description** — what the project covers
   - **Owners** — who's responsible for decisions
4. Set status to **In Progress** and save

Your project is now ready. Create tasks under it, assign agents, and start running work.

---

## Verify your setup

A quick sanity check that everything is wired up:

1. **Packs** — Agents appear in the **Agents** sidebar (orchestrators, executors, reviewers, etc.)
2. **Providers** — At least one provider shows **Enabled: Yes** in Settings > Providers
3. **Presets** — At least one preset appears in Settings > Agent Presets
4. **Project** — A project exists with status **In Progress**

If all four check out, you're ready to launch your first agent.

---

## Recommended defaults

- **Start local-only** if you're evaluating — an Ollama provider works offline with no API keys
- **Keep worktree creation enabled** on presets so agent changes are always isolated
- **Use descriptive preset keys** — you'll see them in every session record and they make filtering easy
- **Set at least one project owner** — reviews and approvals route through ownership

---

## Next steps

Configuration is done. Head to [Use Valdr](/valdr/docs/getting-started/usage/) to run your first workflow, or jump straight to [Launching Agents](/valdr/docs/ui/tasks/agent-launch/) to put your presets to work.