nemo-demo.mp4
- 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
mistral-nemo
,OpenAI
, orClaude
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
- Join our community - Nemo Agent Telegram Group
leetcode
hardsfastapi
orflask
APIsflask
web appsstreamlit
appstkinter
appsjupyter notebook
- Note:
OpenAI
>Claude
>mistral-nemo
for most coding projects - Note: Not all runs will be successful with all models
- Python 3.9 or higher
- OpenAI or Claude API KEY
- Mac or Linux
- Install OpenAI or Claude API KEY for
zsh
shellecho 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.zshrc
orecho 'export ANTHROPIC_API_KEY="YOUR_API_KEY"' >> ~/.zshrc
pip install nemo-agent
- You are ready to use
nemo-agent
- Python 3.9 or higher
- Ollama running
mistral-nemo
- Linux with minimum specs of Ubuntu 24.04 with RTX 4070
- Ollama install instructions:
curl -fsSL https://ollama.com/install.sh | sh
ollama pull mistral-nemo
pip install nemo-agent
- You are ready to use
nemo-agent
ollama
:nemo-agent --provider ollama
openai
:nemo-agent --provider openai
claude
:nemo-agent --provider claude
- Documentation files must be either: .md (Markdown) or .txt (Text) and be located in a folder
nemo-agent --docs example_folder
- 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
nemo-agent --code example_folder
- Data files must be .csv (CSV) and be located in a folder
nemo-agent --data example_folder
nemo-agent "create a fizzbuzz script"
- Prompt file must be markdown (.md) or text files (.txt)
nemo-agent --file example.md
ornemo-agent --file example.txt
cd generated_project_folder
source .venv/bin/activate
python main.py
ollama
ismistral-nemo
(default model)openai
isgpt-4o
claude
isclaude-3-5-sonnet-20241022
nemo-agent "my_prompt" --provider ollama --model nemotron
- Supports
o1-mini
ando1-preview
nemo-agent "my prompt" --provider openai --model o1-mini
Contributions to Nemo Agent are welcome! Please feel free to submit a Pull Request.
This project is licensed under the MIT License - see the LICENSE file for details.
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.