Skip to main content

Your Python AI Coder

Project description

Nemo Agent

PyPI - Version

Nemo Agent

Nemo Agent is your Python AI Coder!

https://github.com/user-attachments/assets/51cf6ad1-196c-44ab-99ba-0035365f1bbd

Features

  • Runs blazing fast
  • Generates Python project structures automatically using uv
  • Writes Python code based on task descriptions
  • Executes development tasks using AI-generated commands
  • Utilizes the Ollama, OpenAI, Claude, or Gemini language models for intelligent code generation
  • Ability to import reference documents to guide the task implementation
  • Allows importing existing code projects in multiple languages to serve as a reference for the task
  • Enables the importation of csv data files to populate databases or graphs
  • Implements best practices in Python development automatically
  • Writes and runs passing tests using pytest up to 80%+ test coverage
  • Automatically fixes and styles code using pylint up to 7+/10
  • Calculates and improves the complexity score using complexipy to be under 15
  • Auto-formats the code with autopep8
  • Shows the token count used for the responses
  • Run via UV (uvx)

Coding Ability

  • leetcode hards
  • fastapi or flask APIs
  • flask web apps
  • streamlit apps
  • tkinter apps
  • jupyter notebook
  • Note: Not all runs will be successful with all models

Install

OpenAI, Claude, or Gemini Install

Requirements

  • Python 3.9 or higher
  • OpenAI, Claude, or Gemini API KEY
  • Mac or Linux
  • No GPU requirement

Requirements Installation

  • Install OpenAI, Claude, or GEMINI API KEY for zsh shell
    • echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.zshrc or
    • echo 'export ANTHROPIC_API_KEY="YOUR_API_KEY"' >> ~/.zshrc or
    • echo 'export GEMINI_API_KEY="YOUR_API_KEY"' >> ~/.zshrc
  • pip install uv
  • uvx nemo-agent - to run nemo-agent

OR

Ollama Install

Requirements

  • Python 3.9 or higher
  • Ollama running qwen2.5-coder:14b
  • Linux with minimum spec of Ubuntu 24.04 with RTX 4070 or;
  • Mac with minimum spec of Mac Mini M2 Pro with 16MB

Requirements Installation

  • Ollama install instructions:
    • curl -fsSL https://ollama.com/install.sh | sh
    • ollama pull qwen2.5-coder:14b
  • pip install uv
  • uvx nemo-agent - to run nemo-agent

Usage

Providers

  • ollama: uvx nemo-agent --provider ollama
  • openai: uvx nemo-agent --provider openai
  • claude: uvx nemo-agent --provider claude
  • gemini: uvx nemo-agent --provider gemini

Import Reference Documentation Into Prompt

  • Documentation files must be either: .md (Markdown) or .txt (Text) and be located in a folder
  • uvx nemo-agent --docs example_folder

Import Existing Code Projects Into Prompt

  • Code files must be either: .py (Python), .php (PHP), .rs (Rust), .js (JavaScript), .ts (TypeScript), .toml (TOML), .json (JSON), .rb (Ruby), or .yaml (YAML) and be located in a folder
  • uvx nemo-agent --code example_folder

Import Data Into Prompt

  • Data files must be .csv (CSV) and be located in a folder
  • uvx nemo-agent --data example_folder

Prompting

CLI

  • uvx nemo-agent "create a fizzbuzz script"

OR

File Prompt

  • Prompt file must be markdown (.md) or text files (.txt)
  • uvx nemo-agent --file example.md or
  • uvx nemo-agent --file example.txt

Run Generated Program

  • cd generated_project_folder
  • source .venv/bin/activate
  • python main.py

Tests

Tests are automatically created and run.

Skipping Tests

You many want to skip tests especially if you are generating a UI application.

  • uvx nemo-agent "create a fizzbuzz script" --tests False

Models

Default Models

  • ollama is qwen2.5-coder:14b
  • openai is gpt-4.1
  • claude is claude-3-7-sonnet-20250219
  • gemini is gemini-2.5-pro-exp-03-25

Select Models

  • uvx nemo-agent "my_prompt" --provider openai --model o3-mini

Supported Models

Ollama

  • Supports any 128k input token models

OpenAI

  • Supports gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, o3-mini, o1-mini, o1, gpt-4o, and gpt-4o-mini

Claude

  • Supports claude-3-7-sonnet-20250219 and claude-3-5-sonnet-20241022

Gemini

  • Supports gemini-2.5-pro-exp-03-25, gemini-2.0-flash, gemini-1.5-pro, gemini-1.5-flash

Contributing

Contributions to Nemo Agent are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Disclaimer

Nemo Agent generates code using an LLM. Every run is different as the LLM generated code is different. While it strives for accuracy and best practices, the generated code should be reviewed and tested before being used in a production environment.

Project details


Release history Release notifications | RSS feed

Download files

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

Source Distribution

nemo_agent-3.8.0.tar.gz (14.5 kB view details)

Uploaded Source

Built Distribution

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

nemo_agent-3.8.0-py3-none-any.whl (13.9 kB view details)

Uploaded Python 3

File details

Details for the file nemo_agent-3.8.0.tar.gz.

File metadata

  • Download URL: nemo_agent-3.8.0.tar.gz
  • Upload date:
  • Size: 14.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.22

File hashes

Hashes for nemo_agent-3.8.0.tar.gz
Algorithm Hash digest
SHA256 18b8d2a44a5f2f1be5e31f0959cd22dcac21acc5fd8f6df3b2591a1c641dc46b
MD5 08a79f5138984e921a8bd803001e8ea8
BLAKE2b-256 d321f6728f23ad641dc5005eff8afd9a793527e72695b903f1f5745b07fa7aaf

See more details on using hashes here.

File details

Details for the file nemo_agent-3.8.0-py3-none-any.whl.

File metadata

  • Download URL: nemo_agent-3.8.0-py3-none-any.whl
  • Upload date:
  • Size: 13.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.22

File hashes

Hashes for nemo_agent-3.8.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ea996f1a01850d8f8a444eb50def78c443a7461cf6be46ef910f1e4323903cf8
MD5 ac7c62d3b83a09fd0360ae688ec31f3a
BLAKE2b-256 0b89125a83cd5bba537d412f3d5e66359ef686ce93439aec7559779a87b5185d

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