This CLI tool converts natural language prompts into executable shell commands using AI, targeting developers and power users who want to accelerate shell command generation without context switching. It offers a streamlined way to get runnable command-line answers, similar to a quick search.

How It Works

The tool leverages Large Language Models (LLMs) via API integrations with providers like OpenAI, Anthropic (Claude), and Google (Gemini). It also supports custom or local models through OpenAI-compatible endpoints. After generating a command, users can edit it in their shell before execution, ensuring safety and allowing for modifications.

Quick Start & Requirements

1. Clone the repository: git clone https://github.com/context-labs/uwu.git && cd uwu
2. Install dependencies and build: bun install && bun run build
3. Make the binary executable and move to PATH: chmod +x dist/uwu-cli && mv dist/uwu-cli /usr/local/bin/uwu-cli
4. Configure config.json with API keys for your chosen LLM provider.
5. Add the uwu helper function to your shell configuration (e.g., ~/.zshrc) and reload it (source ~/.zshrc).

Requires Bun runtime. Supports OpenAI, Claude, Gemini, and custom/local LLM endpoints.

Highlighted Details

• Supports multiple LLM providers including OpenAI, Claude, Gemini, and local models via Ollama or LM Studio.
• Allows in-shell editing of generated commands before execution.
• Integrates with shell history for executed commands.
• Provides a uwu-cli binary and a shell helper function for seamless integration.

Maintenance & Community

The project is hosted on GitHub. Contribution guidelines are provided, welcoming pull requests. No specific community channels (like Discord/Slack) or roadmap details are mentioned in the README.

Licensing & Compatibility

Licensed under the MIT License. This permissive license allows for commercial use and integration with closed-source projects.

Limitations & Caveats

The tool relies on external LLM APIs, incurring potential costs and requiring API key management. The effectiveness of command generation is dependent on the quality of the underlying LLM and the clarity of the natural language prompt.