Flux-CLI

Requirements

Minimum Requirements

RequirementMinimum
Python3.10 or higher
RAM512 MB (for the CLI itself; LLM API calls are server-side)
Storage~50 MB for the codebase and dependencies
TerminalAny modern terminal with UTF-8 support
InternetRequired for LLM API calls and web tools
RequirementRecommended
Python3.11+ (better performance)
RAM2 GB+ (for large context windows)
TerminalTerminal with true color support and Unicode
OSmacOS 14+, Linux (any distro), Windows 10+

Python Dependencies

Flux-CLI relies on the following Python packages:

PackagePurposeMinimum Version
pydanticConfiguration and schema validation2.0
richTerminal UI (tables, panels, syntax highlighting)13.0
clickCLI framework for command parsing8.0
openaiLLM API client (OpenAI-compatible)1.0
platformdirsOS-appropriate config and data directories3.0
tomliTOML configuration file parsing2.0
python-dotenvEnvironment variable loading from .env1.0
tiktokenToken counting for context management0.5
httpxHTTP client for web fetch tool0.24
duckduckgo-searchWeb search functionality4.0
fastmcpMCP client for external server integration0.1

LLM Provider Requirements

Flux-CLI supports any OpenAI-compatible API provider. The default is OpenRouter, which provides:

To use a different provider, simply change the BASE_URL and ensure:

OpenRouter Limitations

OpenRouter imposes a max_tokens limit of 4000 on streaming responses. Flux-CLI complies with this by setting max_tokens: 4000 in all API calls. This is configured in client/llm_client.py.

On this page