Cli Anything Ollama

cli-anything-ollama

Local LLM inference and model management via the Ollama REST API. Designed for AI agents and power users who need to manage models, generate text, chat, and create embeddings without a GUI.

Installation

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

pip install cli-anything-ollama

Prerequisites:

• Python 3.10+
• Ollama must be installed and running (ollama serve)

Usage

Basic Commands

# Show helpcli-anything-ollama --help
# Start interactive REPL modecli-anything-ollama
# List available modelscli-anything-ollama model list
# Run with JSON output (for agent consumption)cli-anything-ollama --json model list

REPL Mode

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

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

Command Groups

Model

Model management commands.

Generate

Text generation and chat commands.

Embed

Embedding generation commands.

Server

Server status and info commands.

Session

Session state commands.

Examples

List and Pull Models

# List available modelscli-anything-ollama model list
# Pull a modelcli-anything-ollama model pull llama3.2
# Show model detailscli-anything-ollama model show llama3.2

Generate Text

# Stream text (default)cli-anything-ollama generate text --model llama3.2 --prompt "Explain quantum computing in one sentence"
# Non-streaming with JSON output (for agents)cli-anything-ollama --json generate text --model llama3.2 --prompt "Hello" --no-stream

Chat

# Single-turn chatcli-anything-ollama generate chat --model llama3.2 --message "user:What is Python?"
# Multi-turn chatcli-anything-ollama generate chat --model llama3.2 \  --message "user:What is Python?" \  --message "user:How does it compare to JavaScript?"
# Chat from JSON filecli-anything-ollama generate chat --model llama3.2 --file messages.json

Embeddings

cli-anything-ollama embed text --model nomic-embed-text --input "Hello world"cli-anything-ollama embed text --model nomic-embed-text --input "Hello" --input "World"

Interactive REPL Session

Start an interactive session for exploratory use.

cli-anything-ollama# Enter commands interactively# Use 'help' to see available commands

Connect to Remote Host

cli-anything-ollama --host http://192.168.1.100:11434 model list

State Management

The CLI maintains lightweight session state:

• Current host URL: Configurable via --host
• Chat history: Tracked for multi-turn conversations in REPL
• Last used model: Shown in REPL prompt

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-ollama model list
# JSON output for agentscli-anything-ollama --json model list

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 --no-stream for generate/chat to get complete responses
5. Verify Ollama is running with server status before other commands

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

1.0.1