Skip to main content

System Requirements

Minimum Hardware

ComponentMinimumRecommended
CPU2 cores4+ cores
RAM2 GB8 GB+
Disk500 MB (l3mcore)Depends on local models
GPUNot requiredOptional (for local ONNX/GGUF)
Raspberry Pi

l3mcore is so lightweight that it can run on a Raspberry Pi 4 with 4 GB of RAM. Ideal for homelabs.

Software

  • Python: 3.9 or higher
  • pip: included with Python
  • git: to clone the repository
  • Ollama (optional): if you want to use local backends with Ollama

Python Dependencies

The main dependencies are installed automatically with setup.sh:

flask
sentence-transformers # for ML embeddings
rapidfuzz # for keyword fallback
litellm # for external APIs (OpenAI, Anthropic, etc.)
onnxruntime # for local ONNX models (optional)

OS Compatibility

Operating SystemStatus
Linux (Ubuntu 20.04+, Debian, Arch)Supported
macOS (12+)Supported
Windows (WSL2)Supported via WSL2
Native WindowsNot tested
Raspberry Pi OSSupported