# Install

hiveloom 1.3.0 requires Python 3.11 or newer and is available on
[PyPI](https://pypi.org/project/hiveloom/1.3.0/).

## Install the CLI or Python library

For an isolated CLI, install or upgrade with:

```bash
uv tool install --upgrade 'hiveloom==1.3.0'
hiveloom --version
```

For a Python project, add it as a dependency instead:

```bash
uv add 'hiveloom==1.3.0'
# Alternatively:
# pip install 'hiveloom==1.3.0'
```

Follow the [Quickstart](/quickstart) to build, validate, and dry-run a harness.
Schema/catalog inspection and dry-run make no model call; declared MCP servers
are still contacted for tool discovery during dry-run.

## Workbench

The workbench ships separately as `hiveloom-workbench` on npm. The new Research,
provider settings, harness settings, and fork-resume features require the 0.2.0
workbench and hiveloom 1.3.0. At this documentation release, npm still offers
0.1.0; `npx hiveloom-workbench` and `hiveloom ui` fetch that older release.

Use the tagged source for the new UI now. You need Node.js 20 or newer and uv:

```bash
git clone --branch v1.3.0 https://github.com/FrancescoMrn/hiveloom.git
cd hiveloom
uv sync --extra dev
devtools/ui/dev.sh
# http://127.0.0.1:5173
```

The source launcher installs frontend dependencies on first launch. Open
**Settings → Models** to add a provider and choose the default model. See
[Workbench](/workbench) for provider storage, harness settings, and fallback.

Once workbench 0.2.0 is published, its packaged launcher can be used instead
at `http://127.0.0.1:8770`. Check the
[npm package](https://www.npmjs.com/package/hiveloom-workbench) for availability.

## Develop from the release source

The same tagged checkout provides the runtime and its offline examples:

```bash
uv run hiveloom --version
uv run hiveloom schema --json
uv run hiveloom catalog tools --json
```

Use `uv run hiveloom` for commands inside this checkout. Older
[1.2.0 installation instructions](/v1.2.0/install) remain available.

## Provider credentials

The default executor provider is `claude`, which uses `ANTHROPIC_API_KEY`:

```bash
export ANTHROPIC_API_KEY=sk-...
hiveloom models --json
```

CLI runs read credentials from the process environment or the harness's own
`.env`. Workbench-saved credentials are local to that workbench setup; they
are not automatically exported to a separate CLI process. Local providers
such as Ollama and vLLM do not require a provider key, but do require a running
server. Scripted [lab fixtures](/demos) need neither credentials nor a server.

## Guidance for coding agents

The wheel includes the schema, catalog, reference guides, and focused skills:

```bash
hiveloom guide --list --json
hiveloom guide research --json
```

See [Models and providers](/models) to select an executor, a proposing model,
or a research director. These are separate choices with separate costs.