Quickstart
Prerequisites
- Python ≥3.9 with uv installed
- Docker Desktop, Rancher Desktop, or Podman (16GB RAM, 6 cores recommended)
- A Kubernetes cluster such as Kind, kubectl, Helm
- (optional) Ollama for local LLM inference
Install
# Clone the repository
git clone https://github.com/rossoctl/rossoctl.git
cd rossoctl
# Check out the latest stable release (recommended)
# Find the current version at https://github.com/rossoctl/rossoctl/releases/latest.
git checkout v0.7.0-alpha.6
# Copy and configure secrets (optional)
cp deployments/envs/secret_values.yaml.example deployments/envs/.secret_values.yaml
# Edit deployments/envs/.secret_values.yaml with your values
# Deploy to Kubernetes cluster
scripts/kind/setup-rossoctl.sh --with-ui --with-spire --with-agent-sandbox --with-builds
Tip: To find the latest stable version from the command line:
git tag --list 'v*' --sort=-v:refname | grep -v -E '(alpha|rc)' | head -1
For all available installer options and detailed instructions (including OpenShift), refer to the Installation Guide.
Access the Rossoctl Dashboard
# Show service URLs and credentials
.github/scripts/local-setup/show-services.sh
open http://rossoctl-ui.localtest.me:8080
# Login with credentials from show-services.sh output
Install a self-hosted LLM
(You may skip this step and see Cloud Models if you are using a cloud-hosted LLM).
-
Install Ollama: https://ollama.com/download
-
Pull a model:
ollama pull gpt-4o-mini-2024-07-18 -
Start Ollama (listening on all interfaces):
OLLAMA_HOST=0.0.0.0 ollama serve
Next steps
From the UI you can:
- Import and deploy A2A agents from any framework
- Deploy MCP tools directly from source
- Test agents interactively
- Monitor traces and network traffic
To learn how to deploy agents and MCP tools, follow the Weather Agent Demo — the recommended getting-started tutorial that walks you through deploying an agent and tool via the UI and chatting with it end-to-end. For more demos, see the full demo list.