Skip to main content

Easy-to-use LLM interface to automate file and shell operations.

Project description

aman_llm

aman_llm is a simple Python package that enables AI-powered file and shell operations using Google's Gemini API. It uses agent-based logic to interpret natural language instructions and perform system-level tasks like creating files, navigating directories, and more — all powered by LLMs.


🚀 Installation

pip install aman_llm

🔐 Environment Setup

To use aman_llm, you must provide a Gemini API key.

Step 1: Get Your Gemini API Key

Visit the following URL and generate your API key:

👉 https://aistudio.google.com/app/apikey

Step 2: Create a .env File

In your project root, create a .env file and add the following:

GOOGLE_API_KEY=your-gemini-api-key-here

This key will be used to authenticate with Gemini when calling the LLM.


✅ Example Usage

from aman_llm import llm_call

llm_call("Create a file named 'integer.txt' and write numbers 1 to 10 in it", stream=True)

📂 Features

  • ✅ Create and modify text files using AI
  • ✅ Run shell commands like ls, pwd, mkdir, etc.
  • ✅ Delegate tasks between intelligent agents (File & Shell)
  • ✅ Powered by Google's gemini-2.0-flash model
  • ✅ Stream responses with rich markdown output

✨ Coming Soon

  • More tool integrations (e.g. web scraping, PDF generation)
  • Async version of the LLM interface
  • LangChain-style chaining

📜 License

MIT License


👨‍💻 Created By

Aman Prasad
🔗 Connect on LinkedIn

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

aman_llm-0.1.6.tar.gz (4.4 kB view details)

Uploaded Source

Built Distribution

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

aman_llm-0.1.6-py3-none-any.whl (4.8 kB view details)

Uploaded Python 3

File details

Details for the file aman_llm-0.1.6.tar.gz.

File metadata

  • Download URL: aman_llm-0.1.6.tar.gz
  • Upload date:
  • Size: 4.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.3

File hashes

Hashes for aman_llm-0.1.6.tar.gz
Algorithm Hash digest
SHA256 8da4d90cdb079ab42810dd0523c60f634a7531b34db2c66989f8bf29907f7198
MD5 8cda5de98145e2aff1810d753b9be945
BLAKE2b-256 11bee6fc2d9d2bd38ad3a19b167f11e5368089868327a82bea2107449081f33d

See more details on using hashes here.

File details

Details for the file aman_llm-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: aman_llm-0.1.6-py3-none-any.whl
  • Upload date:
  • Size: 4.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.3

File hashes

Hashes for aman_llm-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 48ce493c8a4994bbf8a1f9c60b1bb04a49b9939d4a49d474e7bc0701c7a3d807
MD5 68b7d5c0fa99cbd039eaf7b045addbad
BLAKE2b-256 b56fff061d882c626f7eeaadd27738c829e7240dee047094082adef8fc6743d6

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