Autohand Code CLI

An autonomous coding agent CLI that reads, reasons, and writes code across your entire project. No context switching. No copy-paste.

Autohand Code CLI is an autonomous LLM-powered coding agent that lives in your terminal. It uses the ReAct (Reason + Act) pattern to understand your codebase, plan changes, and execute them with your approval. It's blazing fast, intuitive, and extensible with a modular skill system.

We built with a minimalistic design philosophy to keep the focus on coding. Just install, run autohand, and start giving instructions in natural language. Autohand handles the rest.

Scale Autohand across your team and CI/CD pipelines to automate repetitive coding tasks, enforce code quality, and accelerate development velocity.

Features

Autonomous Coding: Understands your codebase and executes changes with approval
ReAct Pattern: Combines reasoning and action for intelligent code modifications
Interactive REPL: Full terminal experience with file mentions and slash commands
Modular Skills: Extend functionality with specialized instruction packages
Multi-Provider Support: Works with OpenRouter, Anthropic, OpenAI, and local models
Git Integration: Full version control support with automatic commits
Cross-Platform: Works on macOS, Linux, and Windows

Why Autohand?

No Context Switching: Stay in your terminal, no copy-paste needed
Intelligent Planning: Understands your codebase before making changes
Safe Execution: Requires approval for all modifications
Extensible: Add new skills and customize behavior
Fast: Optimized for quick responses and efficient execution

Installation

Quick Install (Recommended)

curl -fsSL https://autohand.ai/install.sh | bash

Manual Installation

# Clone and build
git clone https://github.com/autohandai/cli.git
cd cli
bun install
bun run build

# Install globally
bun add -g .

Requirements

Bun ≥1.0 (curl -fsSL https://bun.sh/install | bash)
Git (for version control features)
ripgrep (optional, for faster search)

Quick Start

# Interactive mode - start a coding session
autohand

# Command mode - run a single instruction
autohand -p "add a dark mode toggle to the settings page"

# With auto-confirmation
autohand -p "fix the TypeScript errors" -y

# Auto-commit changes after task completion
autohand -p "refactor the auth module" -c

Editor Extensions

Use Autohand directly in your favorite editor:

VS Code

Install the extension from the VS Code Marketplace or via command line:

code --install-extension AutohandAI.vscode-autohand

Zed Editor

Install from the Zed Extensions marketplace.

Usage Modes

Interactive Mode

Launch without arguments for a full REPL experience:

autohand

Features:

Type / for slash command suggestions
Type @ for file autocomplete (e.g., @src/index.ts)
Type ! to run terminal commands (e.g., ! git status, ! ls -la)
Smart Paste: Paste any amount of code (5+ lines shows compact indicator, full content sent to LLM)
Press ESC to cancel in-flight requests
Press Ctrl+C twice to exit

Command Mode (Non-Interactive)

Run single instructions for CI/CD, scripts, or quick tasks:

# Basic usage
autohand --prompt "add tests for the user service"

# Short form
autohand -p "fix linting errors"

# With options
autohand -p "update dependencies" --yes --auto-commit

# Dry run (preview changes without applying)
autohand -p "refactor database queries" --dry-run

CLI Options

Option	Short	Description
`--prompt <text>`	`-p`	Run a single instruction in command mode
`--yes`	`-y`	Auto-confirm risky actions
`--auto-commit`	`-c`	Auto-commit changes after completing tasks
`--dry-run`		Preview actions without applying mutations
`--model <model>`		Override the configured LLM model
`--path <path>`		Workspace path to operate in
`--auto-skill`		Auto-generate skills based on project analysis
`--unrestricted`		Run without approval prompts (use with caution)
`--restricted`		Deny all dangerous operations automatically
`--config <path>`		Path to config file
`--temperature <value>`		Sampling temperature for LLM
`--login`		Sign in to your Autohand account
`--logout`		Sign out of your Autohand account

Agent Skills

Skills are modular instruction packages that extend Autohand with specialized workflows. They work like on-demand AGENTS.md files for specific tasks.

Using Skills

# List available skills
/skills

# Activate a skill
/skills use changelog-generator

# Create a new skill interactively
/skills new

# Auto-generate project-specific skills
autohand --auto-skill

Auto-Skill Generation

Analyze your project and generate tailored skills automatically:

$ autohand --auto-skill
Analyzing project structure...
Detected: typescript, react, nextjs, testing
Platform: darwin
Generating skills...
  ✓ nextjs-component-creator
  ✓ typescript-test-generator
  ✓ changelog-generator

✓ Generated 3 skills in .autohand/skills

Skills are discovered from:

~/.autohand/skills/ - User-level skills
<project>/.autohand/skills/ - Project-level skills
Compatible with Codex and Claude skill formats

See Agent Skills Documentation for creating custom skills.

Slash Commands

Command	Description
`/help`	Display available commands
`/quit`	Exit the session
`/model`	Switch LLM models
`/new`	Start fresh conversation
`/undo`	Revert last changes
`/session`	Show current session details
`/sessions`	List past sessions
`/resume`	Resume a previous session
`/memory`	View/manage stored memories
`/init`	Create `AGENTS.md` file
`/agents`	List sub-agents
`/agents-new`	Create new agent via wizard
`/skills`	List and manage skills
`/skills new`	Create a new skill
`/feedback`	Send feedback
`/formatters`	List code formatters
`/lint`	List code linters
`/completion`	Generate shell completion scripts
`/export`	Export session to markdown/JSON/HTML
`/status`	Show workspace status
`/login`	Authenticate with Autohand API
`/logout`	Sign out
`/permissions`	Manage tool permissions

Tool System

Autohand includes 40+ tools for autonomous coding:

File Operations

read_file, write_file, append_file, apply_patch, search, search_replace, semantic_search, list_tree, create_directory, delete_path, rename_path, copy_path, multi_file_edit

Git Operations

git_status, git_diff, git_commit, git_add, git_branch, git_switch, git_merge, git_rebase, git_cherry_pick, git_stash, git_fetch, git_pull, git_push, auto_commit

Commands & Dependencies

run_command, custom_command, add_dependency, remove_dependency

Planning & Memory

plan, todo_write, save_memory, recall_memory

Configuration

Create ~/.autohand/config.json:

{
  "provider": "openrouter",
  "openrouter": {
    "apiKey": "sk-or-...",
    "model": "anthropic/claude-sonnet-4-20250514"
  },
  "workspace": {
    "defaultRoot": ".",
    "allowDangerousOps": false
  },
  "ui": {
    "theme": "dark",
    "autoConfirm": false
  }
}

Supported Providers

Provider	Config Key	Notes
OpenRouter	`openrouter`	Access to Claude, GPT-4, Grok, etc.
Anthropic	`anthropic`	Direct Claude API access
OpenAI	`openai`	GPT-4 and other models
Ollama	`ollama`	Local models
llama.cpp	`llamacpp`	Local inference
MLX	`mlx`	Apple Silicon optimized

Session Management

Sessions are auto-saved to ~/.autohand/sessions/:

# Resume via command
autohand resume <session-id>

# Or in interactive mode
/resume

Entire Integration

Autohand Code supports Entire for session checkpointing. Entire captures your coding sessions -- prompts, file changes, and token usage -- as git-backed checkpoints that you can rewind to, review, and share.

# Install hooks in this repository
entire enable --agent autohand-code

# Check status
entire status

# Remove hooks
entire disable --agent autohand-code

Once enabled, Entire works automatically through Autohand's hooks system. No changes to your workflow are needed. See the Entire Integration Guide for setup details and troubleshooting.

Security & Permissions

Autohand includes a permission system for sensitive operations:

Interactive (default): Prompts for confirmation on risky actions
Unrestricted (--unrestricted): No approval prompts
Restricted (--restricted): Denies all dangerous operations

Configure granular permissions in ~/.autohand/config.json:

{
  "permissions": {
    "whitelist": ["run_command:npm *", "run_command:bun *"],
    "blacklist": ["run_command:rm -rf *", "run_command:sudo *"]
  }
}

Platform Support

macOS
Linux
Windows

Telemetry & Feedback

Telemetry is disabled by default. Opt-in to help improve Autohand:

{
  "telemetry": {
    "enabled": true
  }
}

When enabled, Autohand collects anonymous usage data (no PII, no code content). See Telemetry Documentation for details.

The backend API is available at: https://github.com/autohandai/api

Development

# Install dependencies
bun install

# Development mode
bun run dev

# Build
bun run build

# Type check
bun run typecheck

# Run tests
bun test

Docker

FROM oven/bun:1
WORKDIR /app
COPY . .
RUN bun install && bun run build
CMD ["./dist/cli.js"]

docker build -t autohand .
docker run -it autohand

Documentation

Playbook - 20 use cases for the software development lifecycle
Features - Complete feature list
Agent Skills - Skills system guide
Configuration Reference - All config options
Entire Integration - Session checkpointing with Entire

Contributing

We welcome contributions! Please read our Contributing Guide for details on how to get involved.

Troubleshooting

Common Issues

Installation fails: Make sure you have Bun installed and up to date.

Permission denied: Check your file permissions and try running with appropriate privileges.

Model not working: Verify your API key and model configuration in ~/.autohand/config.json.

Getting Help

Join our Discord community
Check the documentation
Open an issue on GitHub

Community

Discord: https://discord.com/invite/MWTNudaj8E
GitHub: https://github.com/autohandai/cli
Website: https://autohand.ai
Twitter: @autohandai

Security

Autohand is designed with security in mind:

No Code Execution: Autohand only suggests changes, you approve them
Permission System: Fine-grained control over what operations are allowed
Local Processing: Your code never leaves your machine unless you choose
Open Source: Transparent code that can be audited

License

Apache License 2.0 - Free for individuals, non-profits, educational institutions, open source projects, and companies with ARR under $5M. See LICENSE and COMMERCIAL.md for details.

Links

Website: https://autohand.ai
CLI Install: https://autohand.ai/cli/
GitHub: https://github.com/autohandai/cli
API Backend: https://github.com/autohandai/api
Discord: https://discord.com/invite/MWTNudaj8E

Roadmap

Upcoming Features

Enhanced AI Models: Support for newer models and improved reasoning
Plugin System: Easier way to extend Autohand with custom functionality
Team Collaboration: Features for team-based development workflows
Advanced Testing: Automated test generation and execution
Code Review: AI-powered code review and quality checks

Current Focus

Improving response times and accuracy
Expanding skill library with more specialized workflows
Enhancing the interactive experience with better UI/UX
Adding more provider integrations
Strengthening security and permission systems

Ready to get started? Run autohand in your terminal and experience the future of coding!

Name		Name	Last commit message	Last commit date
Latest commit History 511 Commits
.github		.github
assets		assets
docs		docs
homebrew		homebrew
prd		prd
scripts		scripts
src		src
tests		tests
.env.example		.env.example
.gitignore		.gitignore
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
COMMERCIAL.md		COMMERCIAL.md
CONTRIBUTING.md		CONTRIBUTING.md
LICENSE		LICENSE
README.md		README.md
config.example.json		config.example.json
eslint.config.js		eslint.config.js
install.ps1		install.ps1
install.sh		install.sh
package.json		package.json
tsconfig.json		tsconfig.json
tsup.config.ts		tsup.config.ts
vitest.config.ts		vitest.config.ts
vitest.setup.ts		vitest.setup.ts

Folders and files

Latest commit

History

Repository files navigation

Autohand Code CLI

Features

Why Autohand?

Installation

Quick Install (Recommended)

Manual Installation

Requirements

Quick Start

Editor Extensions

VS Code

Zed Editor

Usage Modes

Interactive Mode

Command Mode (Non-Interactive)

CLI Options

Agent Skills

Using Skills

Auto-Skill Generation

Slash Commands

Tool System

File Operations

Git Operations

Commands & Dependencies

Planning & Memory

Configuration

Supported Providers

Session Management

Entire Integration

Security & Permissions

Platform Support

Telemetry & Feedback

Development

Docker

Documentation

Contributing

Troubleshooting

Common Issues

Getting Help

Community

Security

License

Links

Roadmap

Upcoming Features

Current Focus

About

Topics

Resources

License

Code of conduct

Contributing

Uh oh!

Stars

Watchers

Forks

Releases 55

Packages 0

Uh oh!

Contributors 3

Languages

Packages