janito 4.2.0

OpenAI CLI with Function Calling, MCP Support, and Extensible Tools

janito - an OpenAI CLI with function calling and MCP

📖 Full documentation available at https://ikignosis.org/janito/

Features

• 🔧 Function Calling - Built-in tools for file operations, web search, and more
• 📧 Gmail Integration - Read, search, and manage emails
• ☁️ OneDrive Integration - Browse, upload, download, and share files
• 🔌 MCP Support - Connect to Model Context Protocol servers
• 🧩 Skills - Install and use task-specific skills from GitHub
• 📊 Real-time Progress - Watch tool execution progress as it happens
• 🚀 Easy Setup - Interactive configuration with --config or quick setup with --set flags
• 🔗 Any OpenAI-Compatible API - Works with OpenAI, local servers (LM Studio, Ollama), and custom endpoints

Quick Start

# Install
pip install janito

# Configure interactively
janito --config

# Or set options directly
janito --set provider=openai --set-api-key="sk-your-key" --set model=gpt-4

# Start chatting
janito "Hello!"

Installation

From PyPI

pip install janito

For development setup, see README_DEV.md.

Configuration

Interactive Setup

janito --config

You'll be prompted for:

• Provider - openai or custom
• API Key - Masked for security
• Model - e.g., gpt-4, gpt-3.5-turbo
• Context Window - Max tokens (default: 65536)

Quick Configuration with --set

Set options directly from the command line:

# Single key-value
janito --set model=gpt-4

# Multiple keys (batch set)
janito --set provider=custom \
       --set endpoint="https://api.example.com/v1" \
       --set model="my-model"

# Set API key and config together
janito --set-api-key="sk-your-key-here" --set model=gpt-4

You can also use --get, --unset, and --set-secret with multiple values.

View Configuration

janito --show-config

Available Options

Option	Description	Example
provider	Provider name	openai, custom
model	Model name	gpt-4, claude-3-opus
context-window	Context window size	65536

For custom endpoints (base-url), see README_LOCAL.md.

Usage

Single Prompt

janito "What is the capital of France?"

Pipe Input

echo "Tell me a joke" | janito

Interactive Chat

janito

Commands in chat mode:

• exit / quit - End session
• restart - Clear conversation history
• Ctrl+D / Ctrl+Z - Exit

Logging

janito --log=info "Your prompt"      # Info level
janito --log=debug "Your prompt"     # Debug level
janito --log=info,debug "Your prompt" # Multiple levels

Examples

OpenAI

janito --set provider=openai --set-api-key="sk-your-key" --set model=gpt-4 "Explain quantum computing"

Alibaba (Qwen)

Set up your configuration first:

janito --set provider=alibaba \
       --set model="qwen3.6-flash" \
       --set-api-key="sk-your-alibaba-key" \
       --set preserve_thinking=true

Then use it with any prompt:

janito "Explain how AI works"

For more models and configuration options, see docs/configuration/alibaba.md.

Built-in Tools

janito includes tools for common tasks:

Email Integration (Gmail)

# Use Gmail in chat mode
janito --gmail

# Check emails
janito --gmail "Show my unread emails from today"

For full Gmail documentation, see README.gmail.md.

Cloud Storage (OneDrive)

# Authenticate with Microsoft OneDrive
janito --onedrive-auth

# Use OneDrive in chat mode
janito --onedrive

# List files
janito --onedrive "List my files in Documents"

For full OneDrive documentation, see README.onedrive.md.

File Operations

# List files
janito.tools.files.list_files . --recursive --pattern "*.py"

# Read file
janito.tools.files.read_file README.md --max-lines 20

MCP Tools

Connect to MCP servers using the /mcp command inside the interactive shell:

# Add a stdio-based MCP server
/mcp add myserver stdio python -m mcp.server

# Add an HTTP-based MCP server
/mcp add remote http https://api.example.com/mcp

# List configured servers
/mcp list

For full MCP documentation, see README_MCP.md.

Tool Progress Reporting

Tools report progress in real-time:

🔄 Reading files...
📊 Processing: 50/100 files
✅ Completed: 100 files (2.3MB)

Progress messages go to stderr so they don't interfere with tool output.

Error Handling

Exit Code	Meaning
0	Success
1	Configuration or runtime error
130	User cancelled (Ctrl+C)

Dependencies

• Python 3.6+
• openai>=1.0.0
• rich>=10.0.0
• prompt-toolkit>=3.0.0
• requests (for MCP support)

License

MIT License