-
Notifications
You must be signed in to change notification settings - Fork 1
Installation
Jason L. West edited this page Feb 3, 2026
·
3 revisions
- Python 3.12+
- Git
- A local LLM server running an OpenAI-compatible API (Nebulus, Ollama, TabbyAPI, vLLM, etc.)
- Docker (required for Nebulus Swarm)
- Slack workspace (required for Swarm Overlord)
git clone git@github.com:jlwestsr/nebulus-atom.git
cd nebulus-atompython3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtFor development (includes testing and linting tools):
pip install -r requirements-dev.txtCopy the example environment file and edit it:
cp .env.example .envEdit .env with your LLM server details:
NEBULUS_BASE_URL=http://localhost:5000/v1 # Your LLM server URL
NEBULUS_API_KEY=admin # API key (if required)
NEBULUS_MODEL=Meta-Llama-3.1-8B-Instruct-exl2-8_0 # Your model name
NEBULUS_TIMEOUT=300 # Request timeout in seconds
NEBULUS_STREAMING=true # Enable streaming responsesSee Configuration for all available environment variables.
# Run the test suite
python3 -m pytest tests/ -v
# Start the agent
python3 -m nebulus_atom.main startYou should see the Nebulus Atom prompt. Type help or /help to see available commands.
The project uses ruff for linting and formatting via pre-commit hooks:
pre-commit installNebulus Atom requires a local LLM server with an OpenAI-compatible API. Supported servers:
| Server | URL | Notes |
|---|---|---|
| Nebulus | http://localhost:5000/v1 |
Custom server |
| Ollama | http://localhost:11434/v1 |
Easy setup |
| TabbyAPI | http://localhost:5000/v1 |
ExLlamaV2 backend |
| vLLM | http://localhost:8000/v1 |
High throughput |
The server must support the /v1/chat/completions endpoint with tool calling.
For Nebulus Swarm (multi-agent system), additional setup is required. See Nebulus Swarm for details.
- Quick Start - Get running in 5 minutes
- CLI Reference - Learn the available commands
- Configuration - Customize your setup