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.

RAG & Vector Databases

Vector Databases

Power your agents with Retrieval-Augmented Generation. 8 vector databases, universal configuration, MCP integration. Same RAG works across all 8 frameworks.

Works with:

DSPy

OpenAI SDK

CrewAI

Google ADK

Microsoft

DeepAgents

Pydantic AI

Vector Databases

Framework Support

✓

MCP Integration

✓

GEPA Optimization

Retrieval-Augmented Generation

What is RAG?

RAG enhances AI agents by providing access to external knowledge sources. Instead of relying solely on pre-trained knowledge, agents retrieve relevant information from your documents to provide accurate, up-to-date responses.

Semantic Search

Find relevant information based on meaning, not just keywords.

Knowledge Grounding

Ground AI responses in your actual documents and data.

Context Retrieval

Automatically retrieve relevant context for each query.

MCP Integration

Hybrid retrieval

Configuration:

retriever_type: surrealdb
vector_store:
  url: surrealkv://./.superoptix/surreal.db
  namespace: test
  database: test
  vector_field: embedding

Embedded Demo Docker Demo Framework Guide

Database Comparison

Database	Scale	Setup	Best For	Performance
ChromaDB	Small-Medium	Zero config	Development	Good
LanceDB	Medium-Large	Zero config	Production	Excellent
Weaviate	Large	Docker	Enterprise	Excellent
Qdrant	Large	Docker	High-throughput	Blazing
Milvus	Massive	Docker Compose	Distributed	Enterprise
SurrealDB	Small-Large	Embedded/Docker	Hybrid + metadata-aware RAG	Flexible

Universal Configuration

RAG Setup

Same RAG configuration works across all 8 frameworks. Just add the rag section to your playbook.

# Basic RAG configuration (works with any framework)

spec:
  target_framework: openai  # or dspy, crewai, google-adk, etc.
  rag:
    enabled: true
    retriever_type: chroma  # or lancedb, weaviate, qdrant, milvus, surrealdb
    config:
      top_k: 5
      chunk_size: 512
      chunk_overlap: 50
    vector_store:
      embedding_model: sentence-transformers/all-MiniLM-L6-v2
      collection_name: knowledge_base

Universal Workflow

$ super agent compile <agent>RAG automatically configured

$ super agent evaluate <agent>Test with knowledge retrieval

$ super agent optimize <agent> --auto mediumGEPA optimizes RAG-enhanced agents

$ super agent run <agent>Use with RAG-enhanced responses

Model Context Protocol

MCP Integration

Combine RAG with MCP for advanced tool and data access. Connect to filesystems, databases, APIs, and Git repositories.

Filesystem

Access local files and directories

Git Repository

Search code and commit history

Database

Query SQL and NoSQL databases

API Endpoints

Connect to REST and GraphQL APIs

Protocol-First Agents

Dataset Import

Best Practices

Document Quality

Use high-quality, relevant documents
Include comprehensive metadata
Regular updates and maintenance

Chunking Strategy

Choose appropriate chunk sizes (512-1024)
Use overlap to maintain context
Consider semantic boundaries

Embedding Models

Use domain-appropriate models
Consider multilingual needs
Balance quality vs performance

Database Selection

ChromaDB for development
LanceDB/Qdrant for production
Milvus for massive scale

Performance Tuning

Monitor retrieval latency
Optimize chunk sizes
Implement caching strategies

GEPA Optimization

Enable RAG optimization
Use auto: medium for start
Monitor relevance metrics

Power Your Agents with RAG

From lightweight ChromaDB to enterprise Milvus. Choose the right vector database and start building knowledge-grounded agents today.

ChromaDB Demo •LanceDB Demo •MCP Guide