tlm

tlm is a terminal assistant for people who want help writing shell commands or understanding commands they've found elsewhere. It uses local models through Ollama rather than a cloud AI service.

• Command suggestions: Describe a task in plain language and get a one-line command suited to your detected Bash, Zsh or PowerShell shell.
• Command explanations: Give tlm an unfamiliar command to see what it does before using it.
• Questions with context: Ask questions using local files as context, such as code in a repository.
• Model choice: Use models such as Llama 3.3, Phi4, DeepSeek-R1 or Qwen for command assistance.

tlm works offline on macOS, Linux and Windows without an API key. It's open source under the Apache 2.0 license.