Skip to main content

Toad terminal

Toad is a universal terminal interface for AI agents, created by Will McGugan, the creator of the popular Python libraries Rich and Textual.

The name comes from "textual code"—combining the Textual framework with coding assistance.

Toad Terminal Interface

Why Toad?

Toad provides a modern terminal user experience that addresses several limitations common to existing terminal-based AI tools:

  • No flickering or visual artifacts - Toad can update partial regions of the screen without redrawing everything
  • Scrollback that works - You can scroll back through your conversation history and interact with previous outputs
  • A unified experience - Instead of learning different interfaces for different AI agents, Toad provides a consistent experience across all supported agents through ACP

Faheem Code is included as a recommended agent in Toad's agent store.

Prerequisites

Before using Toad with Faheem Code:

  1. Faheem Code CLI installed - See Installation
  2. LLM settings configured - Run faheemcode and use /settings

Installation

Install Toad using uv:

uvx batrachian-toad

For more installation options and documentation, visit batrachian.ai.

Setup

Using the agent store

The easiest way to set up Faheem Code with Toad:

  1. Launch Toad: uvx batrachian-toad
  2. Open Toad's agent store
  3. Find Faheem Code in the list of recommended agents
  4. Click Install to set up Faheem Code
  5. Select Faheem Code and start a conversation

The install process runs:

uv tool install faheemcode --python 3.12 && faheemcode login

Manual configuration

You can also launch Toad directly with Faheem Code:

toad acp "faheemcode acp"

Usage

Basic usage

# Launch Toad with Faheem Code
toad acp "faheemcode acp"

With command line arguments

Pass Faheem Code CLI flags through Toad:

# Use LLM-based approval mode
toad acp "faheemcode acp --llm-approve"

# Auto-approve all actions
toad acp "faheemcode acp --always-approve"

Resume a conversation

Resume a specific conversation by ID:

toad acp "faheemcode acp --resume abc123def456"

Resume the most recent conversation:

toad acp "faheemcode acp --resume --last"

Advanced configuration

Combined options

# Resume with LLM approval
toad acp "faheemcode acp --resume --last --llm-approve"

Environment variables

Pass environment variables to Faheem Code:

LLM_API_KEY=your-key toad acp "faheemcode acp"

Troubleshooting

"faheemcode" command not found

Ensure Faheem Code is installed:

uv tool install faheemcode --python 3.12

Verify it's in your PATH:

which faheemcode

Agent doesn't respond

  1. Check your LLM settings: faheemcode then /settings
  2. Verify your API key is valid
  3. Check network connectivity to your LLM provider

Conversation not persisting

Conversations are stored in ~/.faheem-code/conversations. Ensure this directory exists and is writable.

See also