---
title: Getting started
description: Pick where to start with venom, whether you use the CLI, run your own models, use Venom Cloud or build an app on the harness.
section: getting-started
order: 0
audience: [user, operator, builder, agent]
sources: [README.md, docs/getting-started.md]
features: [getting-started.quickstart]
---

Venom is the agent-native operating layer you own: a workspace of apps for people and agents, priced on usage and outcomes instead of seats, a coding agent, and the model infrastructure under them, on models and machines you choose. It runs in Venom Cloud, in your cloud or on your servers; [Choose how to run Venom](/docs/getting-started/choose-how-to-run.md) compares them, and [Products](/docs/products.md) lists every product. The coding agent works with no one else's servers, and every piece works on its own:

| Piece | What it is | Start here |
|---|---|---|
| venom CLI | A coding agent for your terminal, under permission rules you set, with an OS sandbox on macOS and Linux. | [venom CLI quickstart](/docs/getting-started/cli-quickstart.md) |
| Venom Cloud | One OpenAI-compatible endpoint for your own GPUs, trusted public nodes and provider keys, with keys, budgets and logs per key group. | [Venom Cloud quickstart](/docs/getting-started/cloud-quickstart.md) |
| Orchestrator | A self-hosted OpenAI-compatible gateway in Go in front of vLLM, SGLang, llama.cpp, Ollama and cloud providers. | [Local or cloud models](/docs/getting-started/local-or-cloud.md#orchestrator), then the [Orchestrator API](/docs/api/orchestrator) |
| Desktop daemon | The orchestrator and a dashboard on your own machine, without Docker, for local models. | [Local or cloud models](/docs/getting-started/local-or-cloud.md#daemon) |
| Harness and `venom serve` | The agent harness as a library, and the same sessions over HTTP with Server-Sent Events, for building your own agent apps. | [Harness server API](/docs/api/harness-server) |

## The path through this section {#path}

1. [Install venom](/docs/getting-started/install.md) on macOS, Linux or Windows.
2. [Local or cloud models](/docs/getting-started/local-or-cloud.md): point venom at Ollama, your own orchestrator, Venom Cloud or a provider.
3. [venom CLI quickstart](/docs/getting-started/cli-quickstart.md): a first session, permission modes and `venom doctor`.
4. [Your first gear](/docs/getting-started/first-gear.md): switch between cheap, strong and local models in one keystroke.
5. [Troubleshooting](/docs/getting-started/troubleshooting.md) when something doesn't work.

The shortest version, for a machine with Ollama:

```bash
curl -fsSL https://raw.githubusercontent.com/elishahbiz/venom-releases/main/install.sh | sh
export PATH="$HOME/.venom/bin:$PATH"
ollama pull qwen3:8b
export VENOM_BASE_URL=http://localhost:11434/v1
cd ~/work/app && venom
```

## Building an app on venom {#builders}

The harness that runs venom's agent loop, permissions, subagents and Claude Code compatibility is a separate library, so you can build your own product on it (a support desk, a collections workflow, an internal tool) without the terminal UI. Two ways in:

- **In Node:** embed `@venom/harness` and drive sessions from your code. The [Harness section](/docs/harness.md) covers it.
- **From any language:** run `venom serve` and use its HTTP API with Server-Sent Events; there is a Python client. The generated reference is at `/docs/api/harness-server`.

Either way the models come from the same endpoint choices as the CLI: see [Local or cloud models](/docs/getting-started/local-or-cloud.md).

## For agents

Every page here is also plain markdown: add `.md` to its URL (for example `/docs/getting-started/cli-quickstart.md`). [`/docs/llms.txt`](/docs/llms.txt) lists every page with a one-line description, and [`/docs/llms-full.txt`](/docs/llms-full.txt) has all of them in one file.


## In this section {#in-this-section}

- [Choose how to run Venom](/docs/getting-started/choose-how-to-run.md): Compare Venom Cloud, your own cloud and your own servers or an air-gapped site, where the data lives in each, what can leave, and where the install guides are.
- [venom CLI quickstart](/docs/getting-started/cli-quickstart.md): Install the venom CLI, point it at a model, run a first session and check the setup with venom doctor.
- [Venom Cloud quickstart](/docs/getting-started/cloud-quickstart.md): Sign up, create an API key, install the venom CLI, point it at Venom Cloud and test it.
- [Install venom](/docs/getting-started/install.md): Install, update and remove the venom CLI on macOS, Linux and Windows, from the release installer, by hand, or from source.
- [Local or cloud models](/docs/getting-started/local-or-cloud.md): Choose where venom's model runs (Ollama on this machine, the desktop daemon, your own orchestrator, Venom Cloud or any OpenAI-compatible provider) and point the CLI at it.
- [Your first gear](/docs/getting-started/first-gear.md): Switch between cheap, normal, strong and local models in one keystroke with gears, build a gear for your budget with the gear wizard, and make it the default.
- [Troubleshooting](/docs/getting-started/troubleshooting.md): Diagnose a venom setup with venom doctor and fix the common install, endpoint, key, model, sandbox and trust problems.
