Cli Anything Novita

cli-anything-novita

A CLI harness for Novita AI - an OpenAI-compatible API service for AI models like DeepSeek, GLM, and others.

Installation

This CLI is installed as part of the cli-anything-novita package:

pip install cli-anything-novita

Prerequisites:

• Python 3.10+
• Novita API key from novita.ai

Usage

Basic Commands

# Show helpcli-anything-novita --help
# Start interactive REPL modecli-anything-novita
# Chat with modelcli-anything-novita chat --prompt "What is AI?" --model deepseek/deepseek-v3.2
# Streaming chatcli-anything-novita stream --prompt "Write a poem about code"
# List available modelscli-anything-novita models
# JSON output (for agent consumption)cli-anything-novita --json chat --prompt "Hello"

REPL Mode

When invoked without a subcommand, the CLI enters an interactive REPL session:

cli-anything-novita# Enter commands interactively with tab-completion and history

Command Groups

Chat

Chat with AI models through the Novita API.

Session

Session management for chat history.

Config

Configuration management.

Utility

Examples

Configure API Key

# Set API key via config file (recommended)cli-anything-novita config set api_key "sk-xxx"
# Or use environment variableexport NOVITA_API_KEY="sk-xxx"

Chat with DeepSeek

# Simple chatcli-anything-novita chat --prompt "Explain quantum computing" --model deepseek/deepseek-v3.2
# Streaming chatcli-anything-novita stream --prompt "Write a Python function to calculate factorial"

Test Connectivity

# Verify API key and connectivitycli-anything-novita test --model deepseek/deepseek-v3.2
# List all available modelscli-anything-novita models

Default Models

The Novita API supports multiple model providers:

Output Formats

All commands support dual output modes:

• Human-readable (default): Tables, colors, formatted text
• Machine-readable (--json flag): Structured JSON for agent consumption

# Human outputcli-anything-novita chat --prompt "Hello"
# JSON output for agentscli-anything-novita --json chat --prompt "Hello"

For AI Agents

When using this CLI programmatically:

1. Always use --json flag for parseable output
2. Check return codes - 0 for success, non-zero for errors
3. Parse stderr for error messages on failure
4. Use absolute paths for all file operations
5. Verify outputs exist after export operations

More Information

• Full documentation: See README.md in the package
• Test coverage: See TEST.md in the package
• Methodology: See HARNESS.md in the cli-anything-plugin

Version

1.0.0