https://github.com/pluja/maestro

Turn natual language into commands. Your CLI tasks, now as easy as a conversation. Run it 100% offline, or use OpenAI's models.
https://github.com/pluja/maestro

ai assistant bash cli golang llama llm openai terminal

Last synced: 7 days ago
JSON representation

Turn natual language into commands. Your CLI tasks, now as easy as a conversation. Run it 100% offline, or use OpenAI's models.

• Host: GitHub
• URL: https://github.com/pluja/maestro
• Owner: pluja
• Created: 2023-11-25T21:43:34.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-06-26T05:11:52.000Z (3 months ago)
• Last Synced: 2024-09-23T11:34:31.017Z (10 days ago)
• Topics: ai, assistant, bash, cli, golang, llama, llm, openai, terminal
• Language: Go
• Homepage:
• Size: 2.1 MB
• Stars: 52
• Watchers: 3
• Forks: 9
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
![maestro banner](banner.png)

`maestro` converts natural language instructions into cli commands. It's designed for both offline use with Ollama and online integration with ChatGPT API.

![](maestro.svg)

## Key Features

- **Ease of Use**: Simply type your instructions and press enter.

- **Direct Execution**: Use the `-e` flag to directly execute commands with a confirmation prompt for safety.

- **Context Awareness**: Maestro understands your system's context, including the current directory, system, and user.

- **Support for Multiple LLM Models**: Choose from a variety of models for offline and online usage.

  - Offline: [Ollama](https://ollama.ai) with [over 40 models available](https://ollama.ai/library).

  - Online: GPT4-Turbo and GPT3.5-Turbo.

- **Lightweight**: Maestro is a single small binary with no dependencies.

## Installation

1. Download the latest binary from the [releases page](https://github.com/pluja/maestro/releases).

2. Execute `./maestro -h` to start.

> Tip: Place the binary in a directory within your `$PATH` and rename it to `maestro` for global access, e.g., `sudo mv ./maestro /usr/local/bin/maestro`.

## Offline Usage with [Ollama](https://ollama.ai)

> [!IMPORTANT]  

> You need at least Ollama v0.1.24 or greater

1. Install Ollama from [here](https://ollama.ai/download) (or use [ollama's docker image](https://hub.docker.com/r/ollama/ollama)).

2. Download models using `ollama pull `. 

   - **Note**: If you haven't changed it, you will need to pull the default model: `ollama pull dolphin-mistral:latest`

3. Start the Ollama server with `ollama serve`.

4. Configure Maestro to use Ollama with `./maestro -set-ollama-url `, for example, `./maestro -set-ollama-url http://localhost:8080`.

## Online Usage with OpenAI's API

1. Obtain an API token from [OpenAI](https://platform.openai.com/).

2. Set the token using `./maestro -set-openai-token `.

3. Choose between GPT4-Turbo with `-4` flag and GPT3.5-Turbo with `-3` flag.

    - Example: `./maestro -4 `