Axon — AI-powered coding agent

Claude Code-style CLI for AI-assisted code generation, editing, and debugging.

Installation

pip install axons

Note: The package name is axons, but the command you run is axon.

Quick Start

# Set your API key
axon key sk-your-api-key

# (Optional) Set a custom model
axon model gpt-4o

# Or use a local model via Ollama
axon url http://localhost:11434/v1

# Start working
axon

Usage

axon                          Start interactive session
axon key <api_key>            Set your API key
axon model <model_name>       Set the LLM model
axon url <base_url>           Set custom API base URL
axon version                  Show version

Interactive Session Commands

Environment Variables

• OPENAI_API_KEY — OpenAI API key
• ANTHROPIC_API_KEY — Anthropic API key
• AXON_API_KEY — Custom provider API key
• OPENAI_BASE_URL — Custom API base URL
• AXON_MODEL — Default model name
• AXON_PROVIDER — Provider (openai, anthropic, ollama, custom)

Features

• Multi-provider support — OpenAI, Anthropic, Ollama, and OpenAI-compatible APIs
• Built-in coding tools — File editing, patching, code search, command execution, Git integration, and workspace navigation
• Persistent conversation context
• Workspace safety controls — Path confinement, dangerous command blocking, secret-file awareness, and output limits
• MCP server support — Expose Axon's capabilities as MCP tools
• Git-aware workflows — Status, diff, commit, and history tools

How It Works

1. Install the package with pip install axons
2. Run axon to start an interactive session
3. Give Axon a coding task
4. Axon plans and executes work using its tool system
5. Review the results and continue iterating in the same session

Example

$ axon

> Add type hints to my project and fix any mypy errors.

Axon analyzes the codebase, updates files, runs checks, and reports the changes made.