🐤 The Tofu Multi-LLM Client (beta)

Interact with AI models from the command line, with support for most major LLM providers and a beautiful terminal interface. User- and dev-friendly.

Table of Contents

• 🐤 The Tofu Multi-LLM Client (beta)
  • Table of Contents
  • Installation
    • Usage
    • Options
  • Development or Manual Installation
  • License
  • Contribution

Installation

cargo install tofu-llm

This will automatically install Tofu and make it runnable with tofu. Make sure you have ~/.cargo/bin in your PATH.

You can also build from source if you prefer.

Usage

tofu [OPTIONS] [PROMPT]

Tofu works right out of the box via Pollinations, but to use models like GPT and Gemini, you will need to set your API keys using tofu -k.

Options

• -v, --verbose: Enable verbose output
• -h, --help: Print help
• -V, --version: Print version
• -c, --config: Open the config file in the default editor
• -k, --keys: Open the API keys file in the default editor
• -p <PROFILE>, --profile <PROFILE>: Choose a profile from the config file

Development or Manual Installation

1. Clone the repository:

   git clone https://github.com/teccdev/tofu.git
   cd tofu
   

2. Build the project:

   cargo build
   

3. Test if desired:

   cargo test
   

4. Run:

   cargo run -- --help
   

License

Dual-licensed under either of

• Apache License, Version 2.0 (LICENSE-APACHE or https://www.apache.org/licenses/LICENSE-2.0)
• MIT license (LICENSE-MIT or https://opensource.org/licenses/MIT)

at your option.

Upon stable (1.0.0) release, this license may change. If changed, former versions will remain under their original license(s). Tofu will stay open-source forever.

Contribution

Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, as defined in the Apache-2.0 license, shall be dual licensed as above, without any additional terms or conditions.