Claude Terminal — AI skill for Claude Code
A command-line interface for chatting with Anthropic's Claude AI assistant, with optional long-term memory and cross-platform support.
How to install Claude Terminal
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open munkyfoot/claude-terminal and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Terminal does
A command-line interface for chatting with Anthropic's Claude AI assistant, with optional long-term memory and cross-platform support.
Alternatives in AI
- Hindsight — State-of-the-art long-term memory for AI agents by Vectorize 6.7k ★
- Ccstatusline — by sirmalloc - A highly customizable status line formatter for Claude Code CLI that displays model info, git b 5.5k ★
- Nocturne Memory — A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents 1.3k ★
README
Claude Terminal
Claude Terminal is a Python-based command-line interface (CLI) tool that allows you to interact with Anthropic's Claude, an AI assistant. It provides a convenient way to chat with Claude and get assistance with various tasks, including terminal commands, code, and other queries. Claude Terminal supports function calling, which enables the writing and reading of files based on user interactions.
Features
- Chat with Claude directly from your terminal
- Get assistance with terminal commands specific to your platform (Linux, Windows, or macOS)
- Receive help with code and other queries
- Optionally store conversation history to improve responses over time
- Function calling support, enabling file writing and reading based on user interactions
- Ability to switch between Claude models (Sonnet and Opus) for better responses
- Option to show Claude all files and directories in the current directory (except those specified in the .gitignore file)
Prerequisites
- Python 3.7 or higher
- pip (Python package installer)
- Anthropic API key
Installation
- Clone the repository:
git clone https://github.com/Munkyfoot/claude-terminal.git
- Navigate to the project directory:
cd claude-terminal
- Create a virtual environment:
python -m venv venv
- Activate the virtual environment:
- For Linux/macOS:
source venv/bin/activate
- For Windows:
venv\Scripts\activate
- Install the required dependencies:
pip install -r requirements.txt
- Rename
.env.exampleto.env:
mv .env.example .env
- Then open the
.envfile in a text editor and add your Anthropic API key:
ANTHROPIC_API_KEY="YOUR_API_KEY"
Usage
To run Claude Terminal, use the following command:
python main.py [query] [flags]
query: Optional initial query to start the conversationflags:--memoryor-m: Save/load conversation history to add long-term m
Related Skills
CodeForge
CodeForge — a terminal AI coding assistant in Python (Claude Code-style). Pluggable ReAct agent loop, extensib
Sill Ensoul
Long-term memory for CLI agents — cross-CLI, cross-project, cross-session. OKF Wiki + MCP server, model-agnost
Engram Plugins
Weaviate Engram plugins: long-term, cross-session memory for AI coding assistants.
Mnemon
Self-hosted, cross-device long-term memory for AI agents via MCP — one vault shared across any MCP client (Cla
Memora Customersupportagent
AI customer-support agent with persistent, long-term customer memory. Built with Next.js, Anthropic's Claude,
MultiAgentDocumentAssistant
A multi-agent research paper assistant with durable LangGraph workflows, three-layer long-term memory, hybrid
Related Agents
Memory Searcher
Searches the long-term memory vault and returns a dense answer with path:line citations. Use for broad questio
Account Strategist
Expert post-sale account strategist specializing in land-and-expand execution, stakeholder mapping, QBR facili
Curate Chatlog
Curate the m3-chatlog store — clean, dedupe, decay ephemeral turns, prune abandoned conversations, promote hig