Skip to main content

Full Stack Agentic AI Optimization Framework - Universal GEPA optimizer for major frameworks

Project description

SuperOptiX Logo

SuperOptiX AI

Full Stack Agentic AI Optimization Framework

Evaluation-first workflow, framework-native pipelines, and GEPA optimization.


Quick Install

Recommended CLI install with uv

uv tool install superoptix
super --help

Add framework dependencies in the same tool environment

# OpenAI Agents SDK
uv tool install superoptix --with "superoptix[frameworks-openai]"

# Claude Agent SDK
uv tool install superoptix --with "superoptix[frameworks-claude-sdk]"

# Google ADK
uv tool install superoptix --with "superoptix[frameworks-google]"

# Pydantic AI
uv tool install superoptix --with "superoptix[frameworks-pydantic-ai]"

# DeepAgents
uv tool install superoptix --with "superoptix[frameworks-deepagents]"

# Microsoft Agent Framework (legacy support)
uv tool install superoptix --with "superoptix[frameworks-microsoft]"

# CrewAI (see note below)
uv tool install superoptix --with "superoptix[frameworks-crewai]"

CrewAI and DSPy have dependency constraints that may require separate environments in some setups.

Alternative with pip

pip install superoptix

Requirements: Python 3.11+


Framework Support

SuperOptiX supports compiling and running agents across:

  • DSPy
  • OpenAI Agents SDK
  • Claude Agent SDK
  • Pydantic AI
  • CrewAI
  • Google ADK
  • DeepAgents
  • Microsoft Agent Framework (legacy support)

Core Workflow

# Pull
super agent pull developer

# Compile minimal pipeline
super agent compile developer --framework dspy

# Run
super agent run developer --framework dspy --goal "Design a migration strategy"

# Optional optimization path
super agent compile developer --framework dspy --optimize
super agent optimize developer --framework dspy --auto light

Featured Capabilities

  • RLM support (experimental)
  • StackOne connector integrations for SaaS tools
  • GEPA optimization flow across frameworks
  • Minimal runtime pipelines by default with optional optimization lifecycle
  • Core A2A v1 agent-to-agent interoperability

A2A v1 Support

SuperOptiX implements the core A2A 1.0 protocol shape.

That includes:

  • v1 Agent Cards with supportedInterfaces[]
  • v1 task and message semantics
  • v1 method surface such as SendMessage, GetTask, CancelTask, and SubscribeToTask
  • serving compiled agents over A2A with super agent serve <name> --protocol a2a
  • calling remote A2A agents through the SuperOptiX A2A client
  • packaged A2A demos for DSPy, Pydantic AI, and Google ADK

Install the optional A2A extra:

pip install "superoptix[a2a]"

For the full packaged demo set:

pip install "superoptix[a2a,frameworks-pydantic-ai,frameworks-google]"

For demo details:

  • DSPy demo: no model API key required
  • Pydantic AI demo: no model API key required
  • Google ADK demo: requires GOOGLE_API_KEY

Read more:


Documentation


SuperOptiX Lite (Companion Repo)

For a lightweight, MIT-licensed starter kit focused on OpenAI Agents SDK + GEPA:

git clone https://github.com/SuperagenticAI/superoptix-lite-openai.git

Support


Telemetry

SuperOptiX collects anonymous usage data to improve the tool.

To disable telemetry:

export SUPEROPTIX_TELEMETRY=false

License

Apache License 2.0. See LICENCE.

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

superoptix-0.2.21.tar.gz (5.4 MB view details)

Uploaded Source

Built Distribution

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

superoptix-0.2.21-py3-none-any.whl (1.3 MB view details)

Uploaded Python 3

File details

Details for the file superoptix-0.2.21.tar.gz.

File metadata

  • Download URL: superoptix-0.2.21.tar.gz
  • Upload date:
  • Size: 5.4 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.7

File hashes

Hashes for superoptix-0.2.21.tar.gz
Algorithm Hash digest
SHA256 52c6c9cff11a506770718d4a05c070823182023c6378b5077e6fe8b612e94060
MD5 57305ed226deb3c9e67d5de4ea9981e7
BLAKE2b-256 5b5de8d3a0f8af395490cc787e911251747f756ea1cc807d7877765566c76d16

See more details on using hashes here.

File details

Details for the file superoptix-0.2.21-py3-none-any.whl.

File metadata

  • Download URL: superoptix-0.2.21-py3-none-any.whl
  • Upload date:
  • Size: 1.3 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.7

File hashes

Hashes for superoptix-0.2.21-py3-none-any.whl
Algorithm Hash digest
SHA256 a918849b31df91644df3a2b00a971320f2dd73bb3a8b7a42bd41f445f70127b1
MD5 c09b6232eef353de1f6983f8d506d047
BLAKE2b-256 7c93bef9103854490ac2d66341680369be161763254fed556afb04141c950bdc

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