Full Stack Agentic AI Optimization Framework - Universal GEPA optimizer for major frameworks
Project description
🚀 SuperOptiX AI
Full Stack Agentic AI Optimization Framework
Evaluation-First • Optimization-Core • Multi-Framework • Orchestration-Ready
Universal GEPA optimizer for 6 major AI agent frameworks
🎯 Quick Install
Simple Install (Recommended)
pip install superoptix
Install as a CLI Tool (uv)
uv tool install superoptix
super --help
✅ Includes by Default:
- DSPy - GEPA optimization engine
- MCP Client - Model Context Protocol for tool usage
- Super CLI - Conversational AI-powered CLI
- LiteLLM - Multi-provider LLM inference
- All Core Features - Ready to use out of the box!
Requirements: Python 3.11+
Additional Frameworks (Optional)
# OpenAI Agents SDK
pip install superoptix[frameworks-openai]
# Google ADK
pip install superoptix[frameworks-google]
# Microsoft Agent Framework
pip install superoptix[frameworks-microsoft]
# DeepAgents
pip install superoptix[frameworks-deepagents]
# All frameworks (except CrewAI)
pip install superoptix[all]
CrewAI (Separate Install)
# CrewAI conflicts with DSPy - install separately
pip install superoptix
pip install crewai==1.2.0
With MCP Optimization
pip install superoptix[mcp]
Full guide: docs/setup.md
🪶 SuperOptiX Lite (Open Source Companion)
Looking for a lightweight, MIT-licensed starter kit? Clone the companion repository that powers our OpenAI Agents SDK + GEPA tutorial:
git clone https://github.com/SuperagenticAI/superoptix-lite-openai.git
Included
- ✅ Minimal
superoptix_liteBaseComponent scaffolding to expose GEPA-compatible variables - ✅ Native OpenAI Agents SDK integration tuned for Ollama (Code Reviewer pipeline + tests)
- ✅ Baseline, optimization, and regression scripts that mirror the docs walkthrough
Unlock More with Full SuperOptiX
- 🔓 Universal GEPA optimizer with multi-framework compilers (DSPy, CrewAI*, Google ADK, Microsoft, DeepAgents)
- 🔓 RAG, memory, and SuperNetiX orchestration optimizers
- 🔓
superCLI workflows, observability hooks, and enterprise guardrails
*CrewAI installs separately due to DSPy dependency differences—see install notes above.
When you're ready to graduate from Lite to full production, install the expanded stack:
pip install "superoptix[frameworks-openai]"
Bring the optimized prompts, playbooks, and pipelines you prototype in Lite straight into SuperOptiX for end-to-end automation.
📚 Learn More
| Resource | Description | Link |
|---|---|---|
| 🌐 Website | Learn about our vision and solutions | superoptix.ai |
| 📖 GitHub | Source code and project repository | @SuperagenticAI/superoptix-ai |
| 🪶 SuperOptiX Lite | Open source OpenAI SDK + GEPA demo | @SuperagenticAI/superoptix-lite-openai |
| 📦 PyPI | Install via pip | superoptix |
| 🎯 GEPA Demo | Interactive GEPA optimization demonstrations | @SuperagenticAI/gepa-eval |
🆘 Support
📊 Telemetry
SuperOptiX collects anonymous usage data to help us understand how the tool is used and improve it. This data is anonymous and does not include any sensitive information like API keys, prompt content, or environment variables.
To disable telemetry, set the environment variable:
export SUPEROPTIX_TELEMETRY=false
📄 License
This project is licensed under the Apache License, Version 2.0. See the LICENCE file for details.
🚀 Ready to Build the Future?
Start with SuperOptiX • Read the Docs • Join the Revolution
Powered by DSPy. Refined by Superagentic AI.
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file superoptix-0.2.6.tar.gz.
File metadata
- Download URL: superoptix-0.2.6.tar.gz
- Upload date:
- Size: 3.9 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fb48d3f1e316e94aded749abc60c8c23f14a52bac7f8eaaa29ff6af27c18e253
|
|
| MD5 |
e266764567498b627e671d30178611d6
|
|
| BLAKE2b-256 |
0062c3a46c8825f45f81c56e373000a8c7e574a9a0a16cf0f05532e000ec12cc
|
File details
Details for the file superoptix-0.2.6-py3-none-any.whl.
File metadata
- Download URL: superoptix-0.2.6-py3-none-any.whl
- Upload date:
- Size: 1.4 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8ea527113c5ddeb899dc5d838f0494aea87dab661579bb66b4f5ad1754dd56ac
|
|
| MD5 |
d6b7f48f40452a9c4983b6d488954727
|
|
| BLAKE2b-256 |
805ae16064bfcff403939bf5982417a61ab489b7088d61d571a56402eb95f6c8
|