An agentic CLI that reads, reasons, and writes code across your entire project. No context switching. No copy-paste.
Autohand 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. Built with TypeScript and Bun for blazing-fast performance.
curl -fsSL https://autohand.ai/install.sh | bash# Clone and build git clone https://github.com/autohandai/cli.git cd cli bun install bun run build # Install globally bun add -g .
- Bun ≥1.0 (
curl -fsSL https://bun.sh/install | bash) - Git (for version control features)
- ripgrep (optional, for faster search)
# 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
Launch without arguments for a full REPL experience:
autohand
Features:
- Type
/for slash command suggestions - Type
@for file autocomplete (e.g.,@src/index.ts) - Press
ESCto cancel in-flight requests - Press
Ctrl+Ctwice to exit
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
| 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 |
Skills are modular instruction packages that extend Autohand with specialized workflows. They work like on-demand AGENTS.md files for specific tasks.
# 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
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/skillsSkills 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.
| 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 |
Autohand includes 40+ tools for autonomous coding:
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_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
run_command, custom_command, add_dependency, remove_dependency
plan, todo_write, save_memory, recall_memory
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
}
}| 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 |
Sessions are auto-saved to ~/.autohand/sessions/:
# Resume via command autohand resume <session-id> # Or in interactive mode /resume
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 *"]
}
}- macOS
- Linux
- Windows
Opt-in telemetry helps improve Autohand:
{
"telemetry": {
"enabled": true
}
}The backend API is available at: https://github.com/autohandai/api
# Install dependencies bun install # Development mode bun run dev # Build bun run build # Type check bun run typecheck # Run tests bun test
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- Features - Complete feature list
- Agent Skills - Skills system guide
- Configuration Reference - All config options
Startup-Friendly License: Free for startups with ARR under 1ドルM. See LICENSE for details.
- Website: https://autohand.ai
- CLI Install: https://autohand.ai/cli/
- GitHub: https://github.com/autohandai/cli
- API Backend: https://github.com/autohandai/api