@aiiware/aii

AI-powered CLI assistant with autonomous tool execution. An intelligent agent that can read, write, search, and execute commands in your terminal.

Installation

npm install -g @aiiware/aii

Requirements

• Node.js 18+
• Aii Server running (default: localhost:26169)

Quick Start

# Start interactive agent mode
aii

# Or run a single query
aii "explain what this project does"

# Pipe content for processing
cat error.log | aii "summarize the errors"

# Auto-approve tool execution
aii --auto

Agent Mode (Default)

Aii runs as an intelligent agent that can autonomously execute tools to complete tasks:

aii                    # Start interactive session
aii "your task"        # Run single task and exit

Available Tools

| Tool | Description | |---------------|--------------------------------| | Read | Read file contents | | Write | Create or overwrite files | | Edit | Make targeted edits to files | | Glob | Find files by pattern | | Grep | Search code with regex | | Bash | Execute shell commands | | WebSearch | Search the web | | WebFetch | Fetch and parse web pages |

Interactive Commands

In agent mode, use these commands:

/help              Show available commands
/clear             Clear conversation history
/history           Show conversation history
/stats             Show session statistics (tokens, cost)
/model <model>     Switch LLM model
/provider <name>   Switch LLM provider
/context           View context window usage
/init              Generate AGENTS.md for your project
/init --with-hooks Generate AGENTS.md + hooks.json template
/memory            View loaded project instructions
/memory reload     Hot-reload instructions without restart
/hooks             View configured hooks
/hooks reload      Hot-reload hooks without restart
/exit              Exit the session

Keyboard Shortcuts

| Key | Action | |------------|----------------------------| | Enter | Submit input | | Esc | Cancel current request | | Ctrl+C | Exit immediately | | Up/Down | Navigate input history | | Tab | Autocomplete commands |

Output Modes

aii "query" --clean        # Just the result
aii "query" --standard     # Result + metrics (default)
aii "query" --thinking     # Full reasoning chain

Prompt Templates

Use pre-built templates for common tasks:

aii prompt list                       # List available prompts
aii prompt show <name>                # Show prompt details
aii prompt use <name> --var value     # Use a prompt template

Configuration

aii config show                # Show current configuration
aii config validate            # Validate configuration
aii config set <key> <value>   # Set a configuration value
aii config model <model>       # Change LLM model
aii config provider <provider> # Change LLM provider

Config Files

Configuration is stored in ~/.aii/:

config.yaml - Main configuration:

llm:
  provider: anthropic
  model: claude-sonnet-4
  temperature: 0.7

api:
  url: http://localhost:26169

secrets.yaml - API keys:

anthropic_api_key: sk-ant-...
openai_api_key: sk-...
deepseek_api_key: sk-...

Or use environment variables: ANTHROPIC_API_KEY, OPENAI_API_KEY, DEEPSEEK_API_KEY

CLI Options

| Option | Description | |----------------------|----------------------------------| | --auto | Auto-approve all tool executions | | --clean | Clean output mode | | --standard | Standard output mode (default) | | --thinking | Show full reasoning | | --model <model> | Override LLM model | | --host <host:port> | API server host | | --no-streaming | Disable streaming output | | --quiet | Minimal output | | --verbose | Show detailed stats | | --no-context | Disable context management |

Context Window Management (v0.3.0)

Prevents "token limit exceeded" errors in long conversations with intelligent auto-summarization.

Status Bar Indicator: Shows real-time usage with color-coded alerts (🟢 🟡 🔴)

Dynamic Thresholds: Automatically adjusts based on each model's output capacity

• Claude Sonnet (32% output) → 63% critical threshold
• Gemini Flash (3% output) → 92% critical threshold

Auto-Summarization: Older messages summarized when reaching critical threshold (~70%), preserving recent ~30K tokens in full

Commands:

• /context - View detailed usage breakdown
• /context clear - Manually trigger summarization

Project Instructions (v0.5.0)

Teach the agent your project's conventions. Create an AGENTS.md file in your project root, and the agent will automatically learn your coding standards, commands, and rules.

Quick Setup

# Auto-generate AGENTS.md by analyzing your project
/init

# View what instructions are loaded
/memory

The /init command detects your language, framework, build commands, and generates a customized AGENTS.md. Edit it to add your team's conventions.

Supported Files

The agent discovers instruction files in this priority order:

• AII.md or AGENTS.md in project root
• ~/.aii/AGENTS.md for global preferences

Example AGENTS.md

# My Project

## Commands
- Build: `npm run build`
- Test: `npm test`
- Lint: `npm run lint`

## Coding Standards
- Use TypeScript strict mode
- Prefer async/await over callbacks
- Maximum line length: 100

## Safety Rules
Never modify without asking:
- .env files
- Database migrations

Hooks (v0.5.0)

Extend agent behavior with custom scripts. Create .aii/hooks.json to run scripts before/after tool execution:

# Generate a hooks template
/init --with-hooks

# View configured hooks
/hooks

Hooks let you add validation, logging, or approval gates. See the hooks documentation for details.

System Commands

aii doctor         # System health check
aii --help         # Show help
aii --version      # Show version

Features

• Autonomous Agent: Executes multi-step tasks with tool use
• Real-time Streaming: Token-by-token response display
• Interactive Mode: Multi-turn conversations with full context
• Tool Execution: Read, write, search, and run commands
• Multiple Providers: Claude, GPT, Gemini, DeepSeek
• Prompt Templates: Pre-built templates for common tasks
• Project Instructions: Teach the agent your conventions with AGENTS.md
• Input History: Navigate previous inputs with arrow keys
• Cancellation: Press Esc to cancel any request

Links

• Website: aiiware.com
• Issues & Feedback: GitHub

License

Proprietary - Copyright 2025-present AiiWare.com. All Rights Reserved.