solana-agent 22.0.6__py3-none-any.whl → 22.0.8__py3-none-any.whl

{solana_agent-22.0.6.dist-info → solana_agent-22.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: solana-agent
-Version: 22.0.6
+Version: 22.0.8
 Summary: Agentic IQ
 License: MIT
 Keywords: ai,openai,ai agents,agi
@@ -25,12 +25,13 @@ Description-Content-Type: text/markdown
 # Solana Agent
 
 [![PyPI - Version](https://img.shields.io/pypi/v/solana-agent)](https://pypi.org/project/solana-agent/)
-[![PyPI - Downloads](https://img.shields.io/pypi/dm/solana-agent?color=yellow)](https://pypi.org/project/solana-agent/)
+[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)
+[![PyPI - Downloads](https://img.shields.io/pypi/dm/solana-agent)](https://pypi.org/project/solana-agent/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
-[![Python 3.12+](https://img.shields.io/badge/python-3.12+-orange.svg)](https://www.python.org/downloads/)
 [![codecov](https://img.shields.io/codecov/c/github/truemagic-coder/solana-agent/main.svg)](https://codecov.io/gh/truemagic-coder/solana-agent)
 [![Build Status](https://img.shields.io/github/actions/workflow/status/truemagic-coder/solana-agent/ci.yml?branch=main)](https://github.com/truemagic-coder/solana-agent/actions/workflows/ci.yml)
 [![Lines of Code](https://tokei.rs/b1/github/truemagic-coder/solana-agent?type=python&category=code&style=flat)](https://github.com/truemagic-coder/solana-agent)
+[![Libraries.io dependency status for GitHub repo](https://img.shields.io/librariesio/github/truemagic-coder/solana-agent)](https://libraries.io/pypi/solana-agent)
 
 ![Solana Agent Logo](https://dl.walletbubbles.com/solana-agent-logo.png?width=200)
 
@@ -41,7 +42,7 @@ Build your AI business in three lines of code!
 ## Why?
 * Three lines of code setup
 * Multi-Agent Swarm
-* Multi-Modal Streaming
+* Multi-Modal Streaming (Text & Audio)
 * Conversational Memory & History
 * Built-in Internet Search
 * Intelligent Routing
@@ -50,15 +51,16 @@ Build your AI business in three lines of code!
 * Simple Business Definition
 * Tested & Secure
 * Built in Python
-* Deployed by [CometHeart](https://cometheart.com) & [WalletBubbles](https://walletbubbles.com)
+* Powers [CometHeart](https://cometheart.com) & [WalletBubbles](https://walletbubbles.com)
 
 ## Features
 
 * Easy three lines of code setup
 * Designed for a multi-agent swarm 
 * Seamless text and audio streaming with real-time multi-modal processing
+* Configurable audio voice characteristics via prompting
 * Persistent memory that preserves context across all agent interactions
-* Quick built-in Internet Search to answer your queries
+* Quick built-in Internet search to answer your queries
 * Streamlined message history for all agent interactions
 * Intelligent query routing to agents with optimal domain expertise or your own custom routing
 * Unified value system ensuring brand-aligned agent responses
@@ -69,7 +71,7 @@ Build your AI business in three lines of code!
 ## Stack
 
 * [Python](https://python.org) - Programming Language
-* [OpenAI](https://openai.com) - LLMs
+* [OpenAI](https://openai.com) - LLM Provider
 * [MongoDB](https://mongodb.com) - Conversational History (optional)
 * [Zep Cloud](https://getzep.com) - Conversational Memory (optional)
 
@@ -249,10 +251,20 @@ async for response in solana_agent.process("user123", "Write me a poem.", intern
     print(response, end="")
 ```
 
-### Customize Audio Voice
+### Customize Speech
 
 This is an audio to audio example using the `audio_instructions` parameter.
 
+You can prompt to control aspects of speech, including:
+
+* Accent
+* Emotional range
+* Intonation
+* Impressions
+* Speed of speech
+* Tone
+* Whispering
+
 ```python
 async for response in solana_agent.process("user123", audio_content, output_format="audio", audio_voice="nova", audio_input_format="webm", audio_output_format="aac", audio_instructions="You speak with an American southern accent"):
     print(response, end="")
@@ -267,7 +279,7 @@ Tools can be used from plugins like Solana Agent Kit (sakit) or via custom inlin
 * Tools do not use OpenAI function calling
 * Tools are async functions
 
-### Tool Usage Example
+### Tool Example
 
 `pip install sakit`
 
@@ -479,3 +491,111 @@ The official example app written in FastAPI and Next.js
 
 This project is licensed under the MIT License - see the LICENSE file for details.
 
+## Agent Framework Comparisons
+
+### Solana Agent vs OpenAI Agents SDK
+
+| Feature                | Solana Agent                                   | OpenAI Agents SDK                              |
+|------------------------|-----------------------------------------------|-----------------------------------------------|
+| **Architecture**       | Service-oriented with query routing           | Agent-based with explicit handoffs            |
+| **Configuration**      | JSON-based config with minimal code           | Python code-based agent definitions           |
+| **Multi-Agent**        | Automatic specialization routing              | Direct agent-to-agent handoffs                |
+| **Memory**             | Integrated MongoDB/Zep persistence            | In-context memory within message history      |
+| **Multi-Modal**        | Full audio/text streaming built-in            | Optional voice support via add-on package     |
+| **Model Support**      | Currently OpenAI focused                      | Any provider with OpenAI-compatible API       |
+| **Tool Integration**   | Class-based tools with registry               | Function decorators with `@function_tool`     |
+| **Debugging**          | Standard logging                              | Advanced tracing with visualization           |
+| **Safety**             | Basic error handling                          | Configurable guardrails for I/O validation    |
+| **Output Handling**    | Streaming yield pattern                       | Structured output types with validation       |
+| **Business Focus**     | Business mission/values framework             | General purpose agent framework               |
+
+---
+
+### Solana Agent vs LangGraph
+
+| Feature                | Solana Agent                                   | LangGraph                                      |
+|------------------------|-----------------------------------------------|-----------------------------------------------|
+| **Architecture**       | Service-oriented with agents                  | Graph-based state machine                     |
+| **Workflow Design**    | Implicit routing by specialization            | Explicit node connections and state transitions |
+| **Learning Curve**     | Simple setup with config objects              | Steeper with graph concepts and states        |
+| **Streaming**          | Native streaming for all I/O                  | Requires additional configuration             |
+| **Visualization**      | None built-in                                 | Graph visualization of agent workflows        |
+| **State Management**   | Implicit state via memory                     | Explicit state transitions and persistence    |
+| **Integration**        | Standalone framework                          | Part of LangChain ecosystem                   |
+| **Flexibility**        | Fixed routing paradigm                        | Highly customizable flow control              |
+
+---
+
+### Solana Agent vs CrewAI
+
+| Feature                | Solana Agent                                   | CrewAI                                        |
+|------------------------|-----------------------------------------------|-----------------------------------------------|
+| **Multi-Agent Design** | Specialist agents with router                 | Agent crews with explicit roles              |
+| **Agent Interaction**  | Query router determines agent                 | Direct agent-to-agent delegation             |
+| **Configuration**      | JSON-based configuration                      | Python class-based agent definitions         |
+| **Task Structure**     | Query-based interactions                      | Task-based with goals and workflows          |
+| **Memory Sharing**     | Shared memory store                           | Agent-specific memories                      |
+| **Human Interaction**  | Built for direct human queries                | Designed for autonomous operation            |
+| **Streaming**          | Native streaming support                      | Limited streaming support                    |
+| **Team Dynamics**      | Flat specialist structure                     | Hierarchical with managers and workers       |
+
+---
+
+### Solana Agent vs PydanticAI
+
+| Feature                | Solana Agent                                   | PydanticAI                                   |
+|------------------------|-----------------------------------------------|---------------------------------------------|
+| **Multi-Modal**        | Full audio/text streaming built-in            | Text output only, input depends on LLM      |
+| **Memory**             | Built-in conversation history                 | Not included                                |
+| **Multi-Agent**        | First-class multi-agent support               | Single agent focus with composition patterns|
+| **Tool Creation**      | Python classes with execute method            | Function decorators with schema             |
+| **Model Support**      | Currently OpenAI focused                      | Integrates with many LLMs                   |
+| **Debugging**          | Standard logging                              | Pydantic Logfire integration                |
+| **Flow Control**       | Implicit routing                              | Python control flow with graph support      |
+
+---
+
+### When to Use Each Framework
+
+#### Choose **Solana Agent** when:
+- You need a simple, quick-to-deploy agent system.
+- Multi-modal support (text/audio) is essential.
+- You want automatic routing between specialized agents.
+- Business mission alignment is important.
+- You prefer configuration over code.
+- Persistent memory across conversations is needed.
+- You want streaming responses out of the box.
+
+#### Choose **OpenAI Agents SDK** when:
+- You need detailed tracing for debugging complex agent workflows.
+- You want explicit control over agent handoffs.
+- Your architecture requires structured output validation.
+- You're using multiple LLM providers with OpenAI-compatible APIs.
+- You need configurable guardrails for safety.
+- You prefer a code-first approach to agent definition.
+
+#### Choose **LangGraph** when:
+- You need complex, multi-step workflows with branching logic.
+- Your use case requires explicit state management.
+- You want to visualize the flow of your agent system.
+- You're already in the LangChain ecosystem.
+- You need fine-grained control over agent decision paths.
+- Your application has complex conditional flows.
+- You want to model your agent system as a state machine.
+
+#### Choose **CrewAI** when:
+- You need agents to work together with minimal human input.
+- Your use case involves complex team collaboration.
+- You need hierarchical task delegation between agents.
+- You want agents with specific roles and responsibilities.
+- Your application requires autonomous operation.
+- You need explicit agent-to-agent communication.
+- Your workflow involves complex multi-step tasks.
+
+#### Choose **PydanticAI** when:
+- You want to use multiple LLM providers in one codebase.
+- You need real-time debugging and monitoring of agent behavior.
+- You require structured responses with validation guarantees.
+- Your application needs dependency injection for easier testing.
+- You want to leverage your existing Pydantic knowledge.
+- You need both simple control flow and complex graph capabilities.

{solana_agent-22.0.6.dist-info → solana_agent-22.0.8.dist-info}/RECORD

@@ -29,7 +29,7 @@ solana_agent/services/__init__.py,sha256=ab_NXJmwYUCmCrCzuTlZ47bJZINW0Y0F5jfQ9Oo
 solana_agent/services/agent.py,sha256=bIVC4VGCv8qS5AF0nh_hfUjz8nu70Owll-VuvHJ9X48,20047
 solana_agent/services/query.py,sha256=os_LRkDIwXQuWW_zJMtm__n0Lvi-AvItdanpCs1bXv0,11362
 solana_agent/services/routing.py,sha256=PMCSG5m3uLMaHMj3dxNvNfcFZaeaDi7kMr7AEBCzwDE,6499
-solana_agent-22.0.6.dist-info/LICENSE,sha256=BnSRc-NSFuyF2s496l_4EyrwAP6YimvxWcjPiJ0J7g4,1057
-solana_agent-22.0.6.dist-info/METADATA,sha256=TTSOlQ4oTi2lhOsJ9i_eVoHkz3We63p5gE4umyPaVwc,14505
-solana_agent-22.0.6.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
-solana_agent-22.0.6.dist-info/RECORD,,
+solana_agent-22.0.8.dist-info/LICENSE,sha256=BnSRc-NSFuyF2s496l_4EyrwAP6YimvxWcjPiJ0J7g4,1057
+solana_agent-22.0.8.dist-info/METADATA,sha256=vOxA88MO2CxulEn1VYPiuU368AUpI00EYyJ99x48jF4,22230
+solana_agent-22.0.8.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+solana_agent-22.0.8.dist-info/RECORD,,