Inference Gateway CLI

A powerful command-line interface for managing and interacting with the Inference Gateway. This CLI provides tools for configuration, monitoring, and management of inference services.

⚠️ Warning

Early Development Stage: This project is in its early development stage and breaking changes are expected until it reaches a stable version.

Always use pinned versions by specifying a specific version tag when downloading binaries or using install scripts.

Table of Contents

• Features
• Installation
• Quick Start
• Commands
• Tools for LLMs
• Configuration
• Tool Approval System
• Shortcuts
• Global Flags
• Examples
• Development
• License

Features

• Automatic Gateway Management: Automatically downloads and runs the Inference Gateway binary (no Docker required!)
• Zero-Configuration Setup: Start chatting immediately with just your API keys in a .env file
• Interactive Chat: Chat with models using an interactive interface
• Status Monitoring: Check gateway health and resource usage
• Conversation History: Store and retrieve past conversations with multiple storage backends
  • Conversation Storage - Detailed storage backend documentation
  • Conversation Title Generation - AI-powered title generation system
• Configuration Management: Manage gateway settings via YAML config
• Project Initialization: Set up local project configurations
• Tool Execution: LLMs can execute whitelisted commands and tools - See all tools →
• Tool Approval System: User approval workflow for sensitive operations with real-time diff visualization
• Agent Modes: Three operational modes for different workflows:
  • Standard Mode (default): Normal operation with all configured tools and approval checks
  • Plan Mode: Read-only mode for planning and analysis without execution
  • Auto-Accept Mode: All tools auto-approved for rapid execution (YOLO mode)
  • Toggle between modes with Shift+Tab
• Token Usage Tracking: Accurate token counting with polyfill support for providers that don't return usage metrics
• Inline History Auto-Completion: Smart command history suggestions with inline completion
• Customizable Keybindings: Fully configurable keyboard shortcuts for the chat interface
• Extensible Shortcuts System: Create custom commands with AI-powered snippets - Learn more →
• MCP Server Support: Direct integration with Model Context Protocol servers for extended tool capabilities - Learn more →

Installation

Using Go Install

go install github.com/inference-gateway/cli@latest

This installs the binary as cli. To rename it to infer:

mv $(go env GOPATH)/bin/cli $(go env GOPATH)/bin/infer

Or use an alias:

alias infer="$(go env GOPATH)/bin/cli"

Using Container Image

# Create network and deploy inference gateway first
docker network create inference-gateway
docker run -d --name inference-gateway --network inference-gateway \
  --env-file .env \
  ghcr.io/inference-gateway/inference-gateway:latest

# Pull and run the CLI
docker pull ghcr.io/inference-gateway/cli:latest
docker run -it --rm --network inference-gateway ghcr.io/inference-gateway/cli:latest chat

Using Install Script

# Latest version
curl -fsSL https://raw.githubusercontent.com/inference-gateway/cli/main/install.sh | bash

# Specific version
curl -fsSL https://raw.githubusercontent.com/inference-gateway/cli/main/install.sh | bash -s -- --version v0.77.0

# Custom installation directory
curl -fsSL https://raw.githubusercontent.com/inference-gateway/cli/main/install.sh | bash -s -- --install-dir $HOME/.local/bin

Manual Download

Download the latest release binary for your platform from the releases page.

Verify the binary (recommended for security):

# Download binary and checksums
curl -L -o infer-darwin-amd64 \
  https://github.com/inference-gateway/cli/releases/latest/download/infer-darwin-amd64
curl -L -o checksums.txt \
  https://github.com/inference-gateway/cli/releases/latest/download/checksums.txt

# Verify checksum
shasum -a 256 infer-darwin-amd64
grep infer-darwin-amd64 checksums.txt

# Install
chmod +x infer-darwin-amd64
sudo mv infer-darwin-amd64 /usr/local/bin/infer

For advanced verification with Cosign signatures, see Binary Verification Guide.

Build from Source

git clone https://github.com/inference-gateway/cli.git
cd cli
go build -o infer cmd/infer/main.go
sudo mv infer /usr/local/bin/

Quick Start

1. Initialize your project:

infer init

This creates a .infer/ directory with configuration and shortcuts.

2. Set up your environment (create .env file):

ANTHROPIC_API_KEY=your_key_here
OPENAI_API_KEY=your_key_here
DEEPSEEK_API_KEY=your_key_here

3. Start chatting:

infer chat

Next Steps

Now that you're up and running, explore these guides:

• Commands Reference - Complete command documentation
• Tools Reference - Available tools for LLMs
• Configuration Guide - Full configuration options
• Shortcuts Guide - Custom shortcuts and AI-powered snippets
• A2A Agents - Agent-to-agent communication setup

Commands

The CLI provides several commands for different workflows. For detailed documentation, see Commands Reference.

Core Commands

infer init - Initialize a new project with configuration and shortcuts

infer init              # Initialize project configuration
infer init --userspace  # Initialize user-level configuration

infer chat - Start an interactive chat session with model selection

infer chat

Features: Model selection, real-time streaming, scrollable history, three agent modes (Standard/Plan/Auto-Accept).

infer agent - Execute autonomous tasks in background mode

infer agent "Please fix the github issue 38"
infer agent --model "openai/gpt-4" "Implement feature from issue #42"
infer agent "Analyze this UI issue" --files screenshot.png

Features: Autonomous execution, multimodal support (images/files), parallel tool execution.

Configuration Commands

infer config - Manage CLI configuration settings

# Agent configuration
infer config agent set-model "deepseek/deepseek-chat"
infer config agent set-system "You are a helpful assistant"
infer config agent set-max-turns 100
infer config agent verbose-tools enable

# Tool management
infer config tools enable
infer config tools bash enable
infer config tools safety enable

# Export configuration
infer config export set-model "anthropic/claude-4.1-haiku"

See Commands Reference for all configuration options.

Agent Management

infer agents - Manage A2A (Agent-to-Agent) agent configurations

infer agents init                    # Initialize agents configuration
infer agents add browser-agent       # Add an agent from the registry with defaults
infer agents add custom https://...  # Add a custom agent
infer agents list                    # List all agents

For detailed A2A setup, see A2A Agents Configuration.

Utility Commands

infer status - Check gateway health and resource usage

infer status

infer conversation-title - Manage AI-powered conversation titles

infer conversation-title generate  # Generate titles for all conversations
infer conversation-title status    # Show generation status

infer version - Display CLI version information

infer version

Tools for LLMs

When tool execution is enabled, LLMs can use various tools to interact with your system. Below is a summary of available tools. For detailed documentation, parameters, and examples, see Tools Reference.

Tool	Purpose	Approval Required	Documentation
Bash	Execute whitelisted shell commands	Optional	Details
Read	Read file contents with line ranges	No	Details
Write	Write content to files	Yes	Details
Edit	Exact string replacements in files	Yes	Details
MultiEdit	Multiple atomic edits to files	Yes	Details
Delete	Delete files and directories	Yes	Details
Tree	Display directory structure	No	Details
Grep	Search files with regex (ripgrep/Go)	No	Details
WebSearch	Search the web (DuckDuckGo/Google)	No	Details
WebFetch	Fetch content from URLs	No	Details
Github	Interact with GitHub API	No	Details
TodoWrite	Create and manage task lists	No	Details
A2A_SubmitTask	Submit tasks to A2A agents	No	Details
A2A_QueryAgent	Query A2A agent capabilities	No	Details
A2A_QueryTask	Check A2A task status	No	Details
A2A_DownloadArtifacts	Download A2A task outputs	No	Details

Tool Configuration:

Tools can be enabled/disabled and configured individually:

# Enable/disable specific tools
infer config tools bash enable
infer config tools write enable

# Configure tool settings
infer config tools grep set-backend ripgrep
infer config tools web-fetch add-domain "example.com"

See Tools Reference for complete documentation.

Configuration

The CLI uses a powerful 2-layer configuration system with environment variable support.

Configuration Quick Start

Create a minimal configuration:

# .infer/config.yaml
gateway:
  url: http://localhost:8080
  docker: true  # Use Docker mode (or false for binary mode)

tools:
  enabled: true
  bash:
    enabled: true

agent:
  model: "deepseek/deepseek-chat"
  max_turns: 50

chat:
  theme: tokyo-night

Configuration Layers

1. Environment Variables (INFER_*) - Highest priority
2. Command Line Flags
3. Project Config (.infer/config.yaml)
4. Userspace Config (~/.infer/config.yaml)
5. Built-in Defaults - Lowest priority

Example:

# Set via environment variable (highest priority)
export INFER_AGENT_MODEL="openai/gpt-4"

# Or via config file
infer config agent set-model "deepseek/deepseek-chat"

# Or via command flag
infer chat --model "anthropic/claude-4"

Key Configuration Options

• gateway.url - Gateway URL (default: http://localhost:8080)
• gateway.docker - Use Docker mode vs binary mode (default: true)
• tools.enabled - Enable/disable all tools (default: true)
• agent.model - Default model for agent operations
• agent.max_turns - Maximum turns for agent sessions (default: 50)
• chat.theme - Chat interface theme (default: tokyo-night)

Environment Variables

All configuration can be set via environment variables with the INFER_ prefix:

export INFER_GATEWAY_URL="http://localhost:8080"
export INFER_AGENT_MODEL="deepseek/deepseek-chat"
export INFER_TOOLS_BASH_ENABLED=true
export INFER_CHAT_THEME="tokyo-night"

Format: INFER_<PATH> where dots become underscores. Example: agent.model → INFER_AGENT_MODEL

For complete configuration documentation, including all options and environment variables, see Configuration Reference.

Tool Approval System

The CLI includes a comprehensive approval system for sensitive tool operations, providing security and visibility into what actions LLMs are taking.

How It Works

When a tool requiring approval is executed:

1. Validation: Tool arguments are validated
2. Approval Prompt: User sees tool details with:
   • Tool name and parameters
   • Real-time diff preview (for file modifications)
   • Approve/Reject/Auto-approve options
3. Execution: Tool runs only if approved

Default Approval Requirements

Tool	Requires Approval	Reason
Write	Yes	Creates/modifies files
Edit	Yes	Modifies file contents
MultiEdit	Yes	Multiple file modifications
Delete	Yes	Removes files/directories
Bash	Optional	Executes system commands
Read, Grep, Tree	No	Read-only operations
WebSearch, WebFetch	No	External read-only
A2A Tools	No	Agent delegation

Approval Configuration

Configure approval requirements per tool:

# Enable/disable approval for specific tools
infer config tools safety enable    # Global approval
infer config tools bash enable       # Enable bash tool

Or via configuration file:

tools:
  safety:
    require_approval: true  # Global default
  write:
    require_approval: true
  bash:
    require_approval: false  # Override for bash

Approval UI Controls

• y / Enter - Approve execution
• n / Esc - Reject execution
• a - Auto-approve (disables approval for session)

Shortcuts

The CLI provides an extensible shortcuts system for quickly executing common commands with /shortcut-name syntax.

Built-in Shortcuts

Core:

• /clear - Clear conversation history
• /exit - Exit chat session
• /help [shortcut] - Show available shortcuts
• /switch [model] - Switch to different model
• /theme [name] - Switch chat theme
• /compact - Compact conversation
• /export [format] - Export conversation

Git Shortcuts (created by infer init):

• /git-status - Show working tree status
• /git-commit - Generate AI commit message from staged changes
• /git-push - Push commits to remote
• /git-log - Show commit logs

SCM Shortcuts (GitHub integration):

• /scm-issues - List GitHub issues
• /scm-issue <number> - Show issue details
• /scm-pr-create [context] - Generate AI-powered PR plan

AI-Powered Snippets

Create shortcuts that use LLMs to transform data:

# .infer/shortcuts/custom-example.yaml
shortcuts:
  - name: analyze-diff
    description: "Analyze git diff with AI"
    command: bash
    args:
      - -c
      - |
        diff=$(git diff)
        jq -n --arg diff "$diff" '{diff: $diff}'
    snippet:
      prompt: |
        Analyze this diff and suggest improvements:
        ```diff
        {diff}
        ```
      template: |
        ## Analysis
        {llm}

Custom Shortcuts

Create custom shortcuts by adding YAML files to .infer/shortcuts/:

# .infer/shortcuts/custom-dev.yaml
shortcuts:
  - name: tests
    description: "Run all tests"
    command: go
    args:
      - test
      - ./...

  - name: build
    description: "Build the project"
    command: go
    args:
      - build
      - -o
      - infer
      - .

Use with /tests or /build.

For complete shortcuts documentation, including advanced features and examples, see Shortcuts Guide.

Global Flags

• -v, --verbose: Enable verbose output
• --config <path>: Specify custom config file path

Examples

Basic Workflow

# Initialize project
infer init

# Start interactive chat
infer chat

# Execute autonomous task
infer agent "Fix the bug in issue #42"

# Check gateway status
infer status

Working on a GitHub Issue

# Start chat
infer chat

# In chat, use shortcuts to get context
/scm-issue 123

# Discuss with AI, let it use tools to:
# - Read files
# - Search codebase
# - Make changes
# - Run tests

# Generate PR plan when ready
/scm-pr-create Fixes the authentication timeout issue

Configuration Example

# Set default model
infer config agent set-model "deepseek/deepseek-chat"

# Enable bash tool
infer config tools bash enable

# Configure web search
infer config tools web-search enable

# Check current configuration
infer config show

Development

For development, use Task for build automation:

task dev   # Format, build, and test
task build # Build binary
task test  # Run tests

See CLAUDE.md for detailed development documentation.

License

MIT License - see LICENSE file for details.