Terminal Pilot brings lightweight AI chat into the terminal
Terminal Pilot is a Python for chatting with directly inside the terminal. It uses free models through OpenRouter and does not require an Electron app. `tp start` opens an interactive chat, and `/model` lets the user switch models during a conversation.
Terminal output can be sent straight to the AI, such as sending an error log and asking why something is crashing. Project files can be loaded into the current conversation with `/read requirements.txt`. The user can also change the on the fly with commands like `/rule pirate`, or load a prompt from a remote Markdown file.
On first run, Terminal Pilot asks for an key and stores it locally, so no extra setup is needed afterward. The project is intentionally small, at about 300 lines of Python, so it stays easy to understand and extend. It is aimed at developers who spend most of their day in the terminal.
Key points
- Terminal Pilot is a Python for AI chat inside the terminal.
- It connects to free models through OpenRouter and stores the API key locally after first setup.
- It supports model switching, file loading, terminal output piping, and changes.
- The codebase is about 300 lines, making it easier for an individual developer to read and modify.
- The target user is a developer who works mainly in the terminal.