Quickstart
1. Install
macOS / Linux (one line):
curl -fsSL https://contenox.com/install.sh | sh
Or download the binary directly from GitHub Releases.
2. Initialize a workspace
Run this once in the project directory you want Contenox to work in:
contenox init
This creates the workspace marker, writes the default chain and HITL policy presets, and ensures the built-in local backend exists.
3. Pull a local model
For the local-first path, pull a curated GGUF model:
contenox model pull granite-3.2-2b
contenox doctor
On a fresh install, the first pulled model becomes default-model, and contenox init sets default-provider to local when no provider was already configured.
Run your first prompt:
contenox "hello, what can you do?"
For a persistent chat session:
contenox chat -e
4. Optional editor use
Contenox can also run inside editor or desktop clients that speak ACP. The same chains, model config, tools, and HITL policy are used either way:
Cloud providers
Contenox needs at least one model to work. Pick the option that fits:
| Option | What you need |
|---|---|
| Built-in local models | Nothing - Contenox downloads and runs GGUF models itself |
| Ollama | Ollama installed locally, or an Ollama Cloud key |
| Google Gemini | A free Gemini API key (no GPU) |
| OpenRouter | One OpenRouter API key for many hosted models |
| OpenAI | An OpenAI API key |
| Anthropic | An Anthropic API key (Claude) |
| Mistral | A Mistral API key |
| AWS Bedrock | An AWS account with Bedrock model access |
If you're not sure, start with built-in local models — no account or API key needed.
Next steps
- Your first chain — author your own agent in five edits
- Core concepts — how chains, tasks, and tools fit together
- MCP integration — connect external tools