What is the A2A (Agent2Agent) protocol?

A2A is the open protocol that lets agents built on different frameworks call each other. Agents publish an Agent Card describing their skills, and other agents read that card to decide whether and how to invoke them.

How do I make my existing agent A2A compliant?

Run super a2a adapt --entrypoint : --framework . SuperOptiX reads your agent's structure, derives its skills, and writes an A2A Agent Card plus a conformant server. Your agent code is not modified.

Which agent frameworks does SuperOptiX support for A2A?

Eight: DSPy, CrewAI, the OpenAI Agents SDK, Pydantic AI, Google ADK, the Claude Agent SDK, DeepAgents and the Microsoft Agent Framework. Adaptation works on agents written directly against those libraries, whether or not SuperOptiX built them.

How conformant is the SuperOptiX A2A implementation?

It records zero failures against the official A2A Technology Compatibility Kit. Every requirement the TCK exercises against the conformance harness passes: 73 of 73 at MUST, 7 of 7 at SHOULD, 4 of 4 at MAY. The TCK also prints a headline percentage of 77.7% at MUST, which counts 25 requirements it cannot exercise here, covering authentication, TLS, Agent Card signing and gRPC.

How do I make my agent more discoverable to other agents?

Optimize the Agent Card text. SuperOptiX scores discovery rate, invocation rate and confusion rate over a query set, then uses GEPA to rewrite skill names, descriptions and tags against that score. Agent behaviour is unchanged.

Is SuperOptiX free and open source?

Yes, under the MIT License. The A2A implementation, the adapt command, the conformance suite, the routing optimizer, the SuperSpec compiler and all eight framework integrations are in the open source package. Install with uv tool install superoptix.

Is there a live A2A agent I can call?

Yes. A SuperOptiX agent runs at https://a2a.superoptix.ai on Google Cloud Run, with its Agent Card published at https://superoptix.ai/.well-known/agent-card.json.

Who builds SuperOptiX?

Superagentic AI, which builds agentic AI infrastructure and offers support and custom engineering engagements.

Google ADK Integration

Google ADK

Google's Agent Development Kit - Code-first Python toolkit optimized for Gemini models with built-in evaluation framework.

Gemini 2.0 Flash Integration

FREE API Tier Available!

Cloud Run / Vertex AI Deployment

🎯 What is Google ADK?

Google's official framework for building AI agents optimized for Gemini models

Gemini 2.0 Flash

Google's latest, fastest model - FREE tier!

Production Deployment

Cloud Run & Vertex AI ready

Built-in Evaluation

Native evaluation framework

Context Caching

Performance optimization

GEPA Optimization

Optimize agent instructions

A2A Protocol

Agent-to-Agent communication

📦 Prerequisites

1. Install SuperOptiX with Google ADK

uv tool install superoptix --with "superoptix[frameworks-google]"

Includes: google-adk 2.7+, SuperOptiX core with GEPA 0.1.4

2. Get a Google API Key (FREE!)

1. Visit Google AI Studio

2. Create a free API key

3. Set environment variable:

export GOOGLE_API_KEY="your-api-key-here"

🚀 Quick Start

Pull Demo Agent

super agent pull assistant_adk

Compile

super agent compile assistant_adk --framework google-adk

Evaluate

export GOOGLE_API_KEY="your-key"  # Required!
super agent evaluate assistant_adk

Optimize

super agent compile assistant_adk --framework google-adk --optimize
super agent optimize assistant_adk --auto light --framework google-adk

Run

super agent run assistant_adk --framework google-adk --goal "What is AI?"

⚙️ Model Configuration

⭐ Recommended

gemini-2.0-flash

Latest, fastest, FREE tier!

Complex tasks

gemini-1.5-pro

More capable, longer context

Simple tasks

gemini-1.5-flash

Fast, efficient

Example Configuration

spec:
  target_framework: google-adk
  language_model:
    provider: google
    model: gemini-2.0-flash  # Free tier!
  persona:
    instructions: |
      You are a helpful AI assistant powered by Google's Gemini.

🎯 What GEPA Optimizes

Primary Target: Instruction

GEPA optimizes the instruction field - the system prompt guiding agent behavior.

Note: Google ADK has 1 optimizable variable like OpenAI SDK (unlike CrewAI with 5 or DSPy with 10+)

Expected Improvement

Baseline 70-80%→ 85-92% (+15-20%)

Baseline 80-90%→ 90-95% (+10-15%)

Baseline 90-95%→ 93-98% (+3-8%)

Example Optimization Transformation

Before Optimization:

You are a helpful assistant.

After GEPA:

You are an expert AI assistant specialized in providing accurate responses...
Your goal is: Deliver comprehensive answers that are:
- Factually accurate and up-to-date
- Well-structured and easy to understand
- Backed by reasoning and examples...

Google ADK vs Other Frameworks

Feature	DSPy	OpenAI SDK	CrewAI	Google ADK
Local Models	❌ Cloud only
Free Tier	N/A	N/A	N/A	Gemini Free!
Multi-Agent	❌	Handoffs	Sequential/Parallel
Built-in Evaluation	DSPy	❌	❌	Native
Production Deploy	DIY	DIY	DIY	Cloud Run/Vertex
Best For	Prompts	Simple	Teams	Google Ecosystem

Best for:

Google Cloud deployments
Gemini models (state-of-the-art!)
Production enterprise systems
Built-in evaluation needs
Agent-to-Agent (A2A) protocol

❌ Not ideal for:

Local-only development (needs API key)
Ollama/open-source models (use DSPy or OpenAI SDK)
Cost-sensitive prototyping (beyond free tier)

📚 Additional Resources

Google ADK Docs

Official documentation

Google ADK GitHub

Source code

Gemini API

Model documentation

SuperOptiX Guide

Full integration guide

Ready to Build with Google Gemini?

Start building AI agents with Google's state-of-the-art Gemini models - FREE tier available!