Skip to main content

SuperGemini Framework Management Hub - AI-enhanced development framework for Gemini single-agent architecture

Project description

SuperGemini v4.3.0 🚀

Try SuperClaude Framework Try SuperQwen Framework

License: MIT PyPI version Version GitHub issues PRs Welcome Contributors

SuperGemini is a meta-programming configuration framework that enhances Gemini CLI with structured development capabilities. It provides 18 slash commands in TOML format, 13 specialized AI agents with Persona Mode, behavioral instructions, and workflow automation for systematic software development.

Quick Start

Installation Methods

Recommended: pipx (Isolated CLI Tool)

# Install with pipx for clean, isolated environment
pipx install SuperGemini

# Setup SuperGemini for Gemini CLI (Choose one)
SuperGemini install --yes                    # Express setup (recommended)
SuperGemini install --profile minimal --yes  # Fastest (core only)
SuperGemini install --profile full --yes     # All features

Alternative: pip (Traditional Installation)

# Install with pip (may cause dependency conflicts)
pip install SuperGemini

# Or in a virtual environment (recommended if using pip)
python -m venv supergemini-env
source supergemini-env/bin/activate  # Linux/Mac
# or: supergemini-env\Scripts\activate  # Windows
pip install SuperGemini

Usage with Gemini CLI

# Example commands after installation:
/sg:analyze src/
/sg:implement user authentication

Why pipx? SuperGemini is a standalone CLI tool. Using pipx:

  • Prevents dependency conflicts with your projects
  • Provides clean uninstallation
  • Automatically manages virtual environments
  • Keeps your system Python clean

Note for pipx users: If you encounter Node.js/npm detection issues during MCP setup, ensure these tools are available in your system PATH.

What is SuperGemini? 💎

SuperGemini transforms Gemini CLI into a structured development platform by providing:

  • 18 Slash Commands: TOML-based commands for systematic workflow automation (/sg:analyze, /sg:implement, etc.)
  • Persona Mode: 13 specialized AI agents that embody specific roles (system-architect, security-engineer, etc.)
  • SuperAgent MCP Support: Optional subagent orchestration via superagent:gemini, matching SuperClaude’s multi-agent workflows when desired
  • Behavioral Instructions: Core principles and rules for consistent development practices
  • Workflow Automation: Systematic approaches to analysis, implementation, and optimization

Unlike traditional tools, SuperGemini uses Persona Mode where Gemini CLI embodies agent roles rather than spawning separate sub-agents.

GitHub Sponsors

Documentation

Getting Started

User Guides

Developer Resources

Reference

Contributing

Current Priorities:

  • 📝 Documentation improvements and usage examples
  • 🎯 TOML command workflow patterns and best practices
  • 🤖 New AI agent personas for specialized domains
  • 🧪 Testing and validation for Gemini CLI integration
  • 🌐 Translation and internationalization

See CONTRIBUTING.md for detailed contribution guidelines.

License

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

Contributors: View all contributors

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

supergemini-4.3.0.tar.gz (415.4 kB view details)

Uploaded Source

Built Distribution

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

supergemini-4.3.0-py3-none-any.whl (208.5 kB view details)

Uploaded Python 3

File details

Details for the file supergemini-4.3.0.tar.gz.

File metadata

  • Download URL: supergemini-4.3.0.tar.gz
  • Upload date:
  • Size: 415.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for supergemini-4.3.0.tar.gz
Algorithm Hash digest
SHA256 6d67c3973342960cedddd0bdcda27e8ce9f72b7eb82d923eaa20e53455c4d464
MD5 58ad5fbb156b2fb422a6bce67d5a7904
BLAKE2b-256 135ebd63b661bda1c869b77d6acf4c3ab51c6142e4baa4a4b70a27276d0f80a3

See more details on using hashes here.

File details

Details for the file supergemini-4.3.0-py3-none-any.whl.

File metadata

  • Download URL: supergemini-4.3.0-py3-none-any.whl
  • Upload date:
  • Size: 208.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for supergemini-4.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 584bbe5deed68dfb16463565f5c2a80dba4bef391967a530c6542b9464085f9b
MD5 0800fcf6905e8f268adc39714069b2ec
BLAKE2b-256 18409b1655ad0968d2f66dbd07ef3419af97e237d0c87a2bc2b4f54604c53815

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