Skip to main content

LLM-powered CLI tool for daily tasks

Project description

Hermano (LLM-powered Assistant for Operations)

Test CLI Test

A powerful CLI tool that leverages large language models to automate daily tasks.

Features

  • EPUB token counter: Calculate how many tokens an EPUB file would use when sent to an LLM
  • More features coming soon!

Installation

Using pip

pip install hermano

Using Homebrew

brew tap manohar/hermano
brew install hermano

Configuration

Hermano requires API keys for various LLM services. You can set these as environment variables:

export OPENAI_API_KEY="your-api-key"
export DEEPSEEK_API_KEY="your-api-key"
export GEMINI_API_KEY="your-api-key"

Alternatively, you can create a .env file in your home directory:

OPENAI_API_KEY=your-api-key
DEEPSEEK_API_KEY=your-api-key
GEMINI_API_KEY=your-api-key

Usage

EPUB Token Counter

hermano epub tokens path/to/your/book.epub

Options:

  • --model: Specify the model to calculate tokens for (default: "gpt-4")
  • --format: Output format (text, json) (default: "text")

Development

Setup with uv (recommended)

uv is a fast Python package installer and resolver that we recommend for development:

# Install uv
pip install uv

# Clone the repository
git clone https://github.com/manohar/hermano.git
cd hermano

# Create and activate a virtual environment 
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install the package in development mode
uv pip install -e .

# Install development dependencies
uv pip install -r requirements-dev.txt

Traditional Setup

git clone https://github.com/manohar/hermano.git
cd hermano
pip install -e ".[dev]"

Testing

pytest

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hermano-0.1.2.tar.gz (5.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

hermano-0.1.2-py3-none-any.whl (5.7 kB view details)

Uploaded Python 3

File details

Details for the file hermano-0.1.2.tar.gz.

File metadata

  • Download URL: hermano-0.1.2.tar.gz
  • Upload date:
  • Size: 5.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.8

File hashes

Hashes for hermano-0.1.2.tar.gz
Algorithm Hash digest
SHA256 e89ba6ca639ec7d43337b917c2e5fc36deb8f5bbf480e551525a6417fd3354ee
MD5 5338c435608c7396c58aa4dbb30c912c
BLAKE2b-256 d2e6d29dfdaedd11860611f585af7243dfbd90caf12896829c4df686df546959

See more details on using hashes here.

File details

Details for the file hermano-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: hermano-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 5.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.8

File hashes

Hashes for hermano-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 39290fab464f15837b1eea059870260a10b0167c5ec3b7ad3dfe9876c09ec260
MD5 b03d647ed9d37322ee93d99f4c611f7b
BLAKE2b-256 aae5047d041f6586a675f801e677bff32f37cbe86083b7206696c87771e78f0a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page