cleanup examples folder

examples/README.md

@@ -7,70 +7,120 @@ This directory contains comprehensive examples demonstrating various capabilitie
 ### Multi-Agent Systems
 
 - **[multi_agent/](multi_agent/)** - Advanced multi-agent patterns including agent rearrangement, auto swarm builder (ASB), batched workflows, board of directors, caching, concurrent processing, councils, debates, elections, forest swarms, graph workflows, group chats, heavy swarms, hierarchical swarms, majority voting, orchestration examples, social algorithms, simulations, spreadsheet examples, and swarm routing.
+  - [README.md](multi_agent/README.md) - Complete multi-agent examples documentation
 
 ### Single Agent Systems
 
 - **[single_agent/](single_agent/)** - Single agent implementations including demos, external agent integrations, LLM integrations (Azure, Claude, DeepSeek, Mistral, OpenAI, Qwen), onboarding, RAG, reasoning agents, tools integration, utils, and vision capabilities.
+  - [README.md](single_agent/README.md) - Complete single agent examples documentation
+  - [simple_agent.py](single_agent/simple_agent.py) - Basic single agent example
 
 ### Tools & Integrations
 
 - **[tools/](tools/)** - Tool integration examples including agent-as-tools, base tool implementations, browser automation, Claude integration, Exa search, Firecrawl, multi-tool usage, and Stagehand integration.
+  - [README.md](tools/README.md) - Complete tools examples documentation
+  - [agent_as_tools.py](tools/agent_as_tools.py) - Using agents as tools
 
 ### Model Integrations
 
 - **[models/](models/)** - Various model integrations including Cerebras, GPT-5, GPT-OSS, Llama 4, Lumo, and Ollama implementations with concurrent processing examples and provider-specific configurations.
+  - [README.md](models/README.md) - Model integration documentation
+  - [simple_example_ollama.py](models/simple_example_ollama.py) - Ollama integration example
+  - [cerebas_example.py](models/cerebas_example.py) - Cerebras model example
+  - [lumo_example.py](models/lumo_example.py) - Lumo model example
 
 ### API & Protocols
 
 - **[swarms_api_examples/](swarms_api_examples/)** - Swarms API usage examples including agent overview, batch processing, client integration, team examples, analysis, and rate limiting.
+  - [README.md](swarms_api_examples/README.md) - API examples documentation
+  - [client_example.py](swarms_api_examples/client_example.py) - API client example
+  - [batch_example.py](swarms_api_examples/batch_example.py) - Batch processing example
 
 - **[mcp/](mcp/)** - Model Context Protocol (MCP) integration examples including agent implementations, multi-connection setups, server configurations, and utility functions.
+  - [README.md](mcp/README.md) - MCP examples documentation
+  - [multi_mcp_example.py](mcp/multi_mcp_example.py) - Multi-MCP connection example
 
 - **[aop_examples/](aop_examples/)** - Agents over Protocol (AOP) examples demonstrating MCP server setup, agent discovery, client interactions, queue-based task submission, and medical AOP implementations.
+  - [README.md](aop_examples/README.md) - AOP examples documentation
+  - [server.py](aop_examples/server.py) - AOP server implementation
 
 ### Advanced Capabilities
 
 - **[reasoning_agents/](reasoning_agents/)** - Advanced reasoning capabilities including agent judge evaluation systems, O3 model integration, and mixture of agents (MOA) sequential examples.
+  - [README.md](reasoning_agents/README.md) - Reasoning agents documentation
+  - [example_o3.py](reasoning_agents/example_o3.py) - O3 model example
+  - [moa_seq_example.py](reasoning_agents/moa_seq_example.py) - MOA sequential example
 
 - **[rag/](rag/)** - Retrieval Augmented Generation (RAG) implementations with vector database integrations including Qdrant examples.
+  - [README.md](rag/README.md) - RAG documentation
+  - [qdrant_rag_example.py](rag/qdrant_rag_example.py) - Qdrant RAG example
 
 ### Guides & Tutorials
 
 - **[guides/](guides/)** - Comprehensive guides and tutorials including generation length blog, geo guesser agent, graph workflow guide, hierarchical marketing team, nano banana Jarvis agent, smart database, web scraper agents, and workshop examples (840_update, 850_workshop).
-
-### Demonstrations
-
-- **[demos/](demos/)** - Domain-specific demonstrations across various industries including apps, charts, crypto, CUDA, finance, hackathon projects, insurance, legal, medical, news, privacy, real estate, science, and synthetic data generation.
-
-### Hackathons
-
-- **[hackathons/](hackathons/)** - Hackathon projects and implementations including September 27 hackathon examples with diet coach agents, nutritional content analysis swarms, and API client integrations.
+  - [README.md](guides/README.md) - Guides documentation
+  - [hiearchical_marketing_team.py](guides/hiearchical_marketing_team.py) - Hierarchical marketing team example
 
 ### Deployment
 
 - **[deployment/](deployment/)** - Deployment strategies and patterns including cron job implementations and FastAPI deployment examples.
+  - [README.md](deployment/README.md) - Deployment documentation
+  - [fastapi/](deployment/fastapi/) - FastAPI deployment examples
+  - [cron_job_examples/](deployment/cron_job_examples/) - Cron job examples
 
 ### Utilities
 
 - **[utils/](utils/)** - Utility functions and helper implementations including agent loader, communication examples, concurrent wrappers, miscellaneous utilities, and telemetry.
-
-### Educational
-
-- **[workshops/](workshops/)** - Workshop examples and educational sessions including agent tools, batched grids, geo guesser, and Jarvis agent implementations.
+  - [README.md](utils/README.md) - Utils documentation
 
 ### User Interface
 
 - **[ui/](ui/)** - User interface examples and implementations including chat interfaces.
+  - [README.md](ui/README.md) - UI examples documentation
+  - [chat.py](ui/chat.py) - Chat interface example
 
 ## Quick Start
 
 1. **New to Swarms?** Start with [single_agent/simple_agent.py](single_agent/simple_agent.py) for basic concepts
 2. **Want multi-agent workflows?** Check out [multi_agent/duo_agent.py](multi_agent/duo_agent.py)
 3. **Need tool integration?** Explore [tools/agent_as_tools.py](tools/agent_as_tools.py)
-4. **Interested in AOP?** Try [aop_examples/example_new_agent_tools.py](aop_examples/example_new_agent_tools.py) for agent discovery
+4. **Interested in AOP?** Try [aop_examples/client/example_new_agent_tools.py](aop_examples/client/example_new_agent_tools.py) for agent discovery
 5. **Want to see social algorithms?** Check out [multi_agent/social_algorithms_examples/](multi_agent/social_algorithms_examples/)
 6. **Looking for guides?** Visit [guides/](guides/) for comprehensive tutorials
-7. **Hackathon projects?** Explore [hackathons/hackathon_sep_27/](hackathons/hackathon_sep_27/) for real-world implementations
+7. **Need RAG?** Try [rag/qdrant_rag_example.py](rag/qdrant_rag_example.py)
+8. **Want reasoning agents?** Check out [reasoning_agents/example_o3.py](reasoning_agents/example_o3.py)
+
+## Key Examples by Category
+
+### Multi-Agent Patterns
+
+- [Duo Agent](multi_agent/duo_agent.py) - Two-agent collaboration
+- [Hierarchical Swarm](multi_agent/hiearchical_swarm/hierarchical_swarm_example.py) - Hierarchical agent structures
+- [Group Chat](multi_agent/groupchat/interactive_groupchat_example.py) - Multi-agent conversations
+- [Graph Workflow](multi_agent/graphworkflow_examples/graph_workflow_example.py) - Graph-based workflows
+- [Social Algorithms](multi_agent/social_algorithms_examples/) - Various social algorithm patterns
+
+### Single Agent Examples
+
+- [Simple Agent](single_agent/simple_agent.py) - Basic agent setup
+- [Reasoning Agents](single_agent/reasoning_agent_examples/) - Advanced reasoning patterns
+- [Vision Agents](single_agent/vision/multimodal_example.py) - Vision and multimodal capabilities
+- [RAG Agents](single_agent/rag/qdrant_rag_example.py) - Retrieval augmented generation
+
+### Tool Integrations
+
+- [Agent as Tools](tools/agent_as_tools.py) - Using agents as tools
+- [Browser Automation](tools/browser_use_as_tool.py) - Browser control
+- [Exa Search](tools/exa_search_agent.py) - Search integration
+- [Stagehand](tools/stagehand/) - UI automation
+
+### Model Integrations
+
+- [OpenAI](single_agent/llms/openai_examples/4o_mini_demo.py) - OpenAI models
+- [Claude](single_agent/llms/claude_examples/claude_4_example.py) - Claude models
+- [DeepSeek](single_agent/llms/deepseek_examples/deepseek_r1.py) - DeepSeek models
+- [Azure](single_agent/llms/azure_agent.py) - Azure OpenAI
+- [Ollama](models/simple_example_ollama.py) - Local Ollama models
 
 ## Documentation
 

examples/aop_examples/client/README.md

@@ -0,0 +1,18 @@
+# AOP Client Examples
+
+This directory contains examples demonstrating AOP (Agents over Protocol) client implementations.
+
+## Examples
+
+- [aop_cluster_example.py](aop_cluster_example.py) - AOP cluster client example
+- [aop_queue_example.py](aop_queue_example.py) - Queue-based task submission
+- [aop_raw_client_code.py](aop_raw_client_code.py) - Raw AOP client implementation
+- [aop_raw_task_example.py](aop_raw_task_example.py) - Raw AOP task example
+- [example_new_agent_tools.py](example_new_agent_tools.py) - New agent tools example
+- [get_all_agents.py](get_all_agents.py) - Agent discovery example
+- [list_agents_and_call_them.py](list_agents_and_call_them.py) - List and call agents
+
+## Overview
+
+AOP client examples demonstrate how to connect to AOP servers, discover available agents, submit tasks, and interact with agents over the protocol. These examples show various client patterns including queue-based submission, cluster management, and agent discovery.
+

examples/aop_examples/discovery/README.md

@@ -0,0 +1,15 @@
+# AOP Discovery Examples
+
+This directory contains examples demonstrating agent discovery mechanisms in AOP.
+
+## Examples
+
+- [example_agent_communication.py](example_agent_communication.py) - Agent communication example
+- [example_aop_discovery.py](example_aop_discovery.py) - AOP discovery implementation
+- [simple_discovery_example.py](simple_discovery_example.py) - Simple discovery example
+- [test_aop_discovery.py](test_aop_discovery.py) - Discovery testing
+
+## Overview
+
+AOP discovery examples demonstrate how agents can discover and communicate with each other over the protocol. These examples show various discovery patterns, agent registration, and communication protocols for distributed agent systems.
+

examples/aop_examples/medical_aop/README.md

@@ -0,0 +1,13 @@
+# Medical AOP Examples
+
+This directory contains medical domain-specific AOP implementations.
+
+## Examples
+
+- [client.py](client.py) - Medical AOP client
+- [server.py](server.py) - Medical AOP server
+
+## Overview
+
+Medical AOP examples demonstrate domain-specific implementations of Agents over Protocol for healthcare applications. These examples show how to structure AOP servers and clients for medical use cases, including patient data handling, medical analysis, and healthcare workflows.
+

examples/aop_examples/utils/README.md

@@ -0,0 +1,16 @@
+# AOP Utils
+
+This directory contains utility functions and helpers for AOP implementations.
+
+## Examples
+
+- [comprehensive_aop_example.py](comprehensive_aop_example.py) - Comprehensive AOP example
+- [network_error_example.py](network_error_example.py) - Network error handling
+- [network_management_example.py](network_management_example.py) - Network management utilities
+- [persistence_example.py](persistence_example.py) - Persistence implementation
+- [persistence_management_example.py](persistence_management_example.py) - Persistence management
+
+## Overview
+
+AOP utils provide helper functions, error handling patterns, network management utilities, and persistence mechanisms for AOP implementations. These examples demonstrate best practices for building robust AOP systems.
+

examples/deployment/cron_job_examples/README.md

@@ -0,0 +1,19 @@
+# Cron Job Examples
+
+This directory contains examples demonstrating scheduled task execution using cron jobs.
+
+## Examples
+
+- [callback_cron_example.py](callback_cron_example.py) - Cron job with callbacks
+- [cron_job_example.py](cron_job_example.py) - Basic cron job example
+- [cron_job_figma_stock_swarms_tools_example.py](cron_job_figma_stock_swarms_tools_example.py) - Figma stock swarms tools cron job
+- [crypto_concurrent_cron_example.py](crypto_concurrent_cron_example.py) - Concurrent crypto cron job
+- [figma_stock_example.py](figma_stock_example.py) - Figma stock example
+- [simple_callback_example.py](simple_callback_example.py) - Simple callback example
+- [simple_concurrent_crypto_cron.py](simple_concurrent_crypto_cron.py) - Simple concurrent crypto cron
+- [solana_price_tracker.py](solana_price_tracker.py) - Solana price tracker cron job
+
+## Overview
+
+Cron job examples demonstrate how to schedule and execute agent tasks on a recurring basis. These examples show various patterns including callback handling, concurrent execution, and domain-specific scheduled tasks like price tracking and stock monitoring.
+

examples/guides/840_update/README.md

@@ -0,0 +1,15 @@
+# 840 Update Examples
+
+This directory contains examples from the 840 update, demonstrating new features and improvements.
+
+## Examples
+
+- [agent_rearrange_concurrent_example.py](agent_rearrange_concurrent_example.py) - Agent rearrangement with concurrency
+- [auto_swarm_builder_example.py](auto_swarm_builder_example.py) - Auto swarm builder example
+- [fallback_example.py](fallback_example.py) - Fallback mechanism example
+- [server.py](server.py) - Server implementation
+
+## Overview
+
+These examples showcase features introduced in the 840 update, including concurrent agent rearrangement, auto swarm building capabilities, and improved fallback mechanisms.
+

examples/guides/850_workshop/README.md

@@ -0,0 +1,18 @@
+# 850 Workshop Examples
+
+This directory contains examples from the 850 workshop, demonstrating advanced multi-agent patterns and AOP integration.
+
+## Examples
+
+- [aop_raw_client_code.py](aop_raw_client_code.py) - Raw AOP client implementation
+- [aop_raw_task_example.py](aop_raw_task_example.py) - Raw AOP task example
+- [moa_seq_example.py](moa_seq_example.py) - Mixture of Agents sequential example
+- [peer_review_example.py](peer_review_example.py) - Peer review pattern
+- [server.py](server.py) - Server implementation
+- [test_agent_concurrent.py](test_agent_concurrent.py) - Concurrent agent testing
+- [uvloop_example.py](uvloop_example.py) - UVLoop integration example
+
+## Overview
+
+These examples from the 850 workshop demonstrate advanced patterns including Agents over Protocol (AOP) integration, mixture of agents, peer review workflows, and high-performance async execution with UVLoop.
+

examples/guides/generation_length_blog/README.md

@@ -0,0 +1,13 @@
+# Generation Length Blog Examples
+
+This directory contains examples related to generation length management and long-form content generation.
+
+## Examples
+
+- [longform_generator.py](longform_generator.py) - Long-form content generator
+- [universal_api.py](universal_api.py) - Universal API for generation
+
+## Overview
+
+These examples demonstrate techniques for managing generation length, creating long-form content, and implementing universal APIs for content generation. Useful for blog posts, articles, and extended text generation tasks.
+

examples/guides/hackathon_judge_agent/README.md

@@ -0,0 +1,13 @@
+# Hackathon Judge Agent
+
+This directory contains a hackathon project judging agent example.
+
+## Examples
+
+- [hackathon_judger_agent.py](hackathon_judger_agent.py) - Hackathon project judging agent
+- [projects.csv](projects.csv) - Sample projects dataset
+
+## Overview
+
+This example demonstrates an agent system designed to evaluate and judge hackathon projects. The agent can analyze project descriptions, assess quality, and provide structured feedback based on predefined criteria.
+

examples/guides/hackathon_judge_agent/hackathon_judger_agent.py

@@ -0,0 +1,120 @@
+from swarms import Agent
+
+HACKATHON_JUDGER_AGENT_PROMPT = """
+## 🧠 **System Prompt: Hackathon Judger Agent (AI Agents Focus)**
+
+**Role:**
+You are an expert hackathon evaluation assistant judging submissions in the *Builders Track*.
+Your task is to evaluate all projects using the provided criteria and automatically identify those related to **AI agents, agentic architectures, or autonomous intelligent systems**.
+
+You must then produce a **ranked report** of the **top 3 AI agent–related projects**, complete with weighted scores, category breakdowns, and short qualitative summaries.
+
+---
+
+### 🎯 **Judging Framework**
+
+Each project is evaluated using the following **weighted criteria** (from the Builders Track official judging rubric):
+
+#### 1. Technical Feasibility & Implementation (30%)
+
+Evaluate how well the project was built and its level of technical sophistication.
+
+* **90–100:** Robust & flawless. Excellent code quality. Seamless, innovative integration.
+* **80–90:** Works as intended. Clean implementation. Effective Solana or system integration.
+* **60–80:** Functional but basic or partially implemented.
+* **0–60:** Non-functional or poor implementation.
+
+#### 2. Quality & Clarity of Demo (20%)
+
+Evaluate the quality, clarity, and impact of the presentation or demo.
+
+* **90–100:** Compelling, professional, inspiring vision.
+* **80–90:** Clear, confident presentation with good storytelling.
+* **60–80:** Functional but unpolished demo.
+* **0–60:** Weak or confusing presentation.
+
+#### 3. Presentation of Idea (30%)
+
+Evaluate how clearly the idea is communicated and how well it conveys its purpose and impact.
+
+* **90–100:** Masterful, engaging storytelling. Simplifies complex ideas elegantly.
+* **80–90:** Clear, structured, and accessible presentation.
+* **60–80:** Understandable but lacks focus.
+* **0–60:** Confusing or poorly explained.
+
+#### 4. Innovation & Originality (20%)
+
+Evaluate the novelty and originality of the idea, particularly within the context of agentic AI.
+
+* **90–100:** Breakthrough concept. Strong fit with ecosystem and AI innovation.
+* **80–90:** Distinct, creative, and forward-thinking.
+* **60–80:** Incremental improvement.
+* **0–60:** Unoriginal or derivative.
+
+---
+
+### ⚖️ **Scoring Rules**
+
+1. Assign each project a **score (0–100)** for each category.
+2. Apply weights to compute a **final total score out of 100**:
+
+   * Technical Feasibility — 30%
+   * Demo Quality — 20%
+   * Presentation — 30%
+   * Innovation — 20%
+3. Filter and **select only projects related to AI agents or agentic systems**.
+4. Rank these filtered projects **from highest to lowest total score**.
+5. Select the **top 3 projects** for the final report.
+
+---
+
+### 🧩 **Output Format**
+
+Create a markdown report of the top 3 projects with how they follow the judging criteria and why they are the best.
+
+---
+
+### 🧭 **Special Instructions**
+
+* Consider “AI agents” to include:
+
+  * Autonomous or semi-autonomous decision-making systems
+  * Multi-agent frameworks or LLM-powered agents
+  * Tools enabling agent collaboration, coordination, or reasoning
+  * Infrastructure for agentic AI development or deployment
+* If fewer than 3 relevant projects exist, output only those available.
+* Use concise, professional tone and evidence-based reasoning in feedback.
+* Avoid bias toward hype; focus on execution, innovation, and ecosystem impact.
+
+---
+
+Would you like me to tailor this further for **automatic integration** into an evaluation pipeline (e.g., where the agent consumes structured project metadata and outputs ranked JSON reports automatically)? That version would include function schemas and evaluation templates.
+
+"""
+
+# Initialize the agent
+agent = Agent(
+    agent_name="Hackathon-Judger-Agent",
+    agent_description="A hackathon judger agent that evaluates projects based on the judging criteria and produces a ranked report of the top 3 projects.",
+    model_name="claude-haiku-4-5",
+    system_prompt=HACKATHON_JUDGER_AGENT_PROMPT,
+    dynamic_temperature_enabled=True,
+    max_loops=1,
+    dynamic_context_window=True,
+    streaming_on=False,
+    top_p=None,
+    output_type="dict",
+)
+
+
+def read_csv_file(file_path: str = "projects.csv") -> str:
+    """Reads the entire CSV file and returns its content as a string."""
+    with open(file_path, mode="r", encoding="utf-8") as f:
+        return f.read()
+
+
+out = agent.run(
+    task=read_csv_file(),
+)
+
+print(out)

examples/guides/hackathon_judge_agent/projects.csv

@@ -0,0 +1,149 @@
+No.,Full Name,Respondent's country,Affiliation,Project Name,Brief Description,Brief Description (English Translation),Storytelling Video OR Article Link,Demo Link,Repository Link,Link to Published Work,Use of Toolkit,"Technical Feasibility 
+& Implementation 
+(30%)","Quality 
+& Clarity of Demo 
+(20%)","Presentation of Idea 
+(30%)","Innovation 
+& Originality of Idea 
+(20%)","Manual
+Total Score",Manual Scoring Feedback
+1,Yuki Sato,Japan,Keio University Blockchain Club,Daiko,Daiko AI tells you when to sell and why based on market data and risk profile.,Daiko AI tells you when to sell and why based on market data and risk profile.,https://www.youtube.com/watch?v=VJYT4-jbT8U,https://app.daiko.ai,https://github.com/Daiko-AI/daiko-ai-mvp-monorepo,https://x.com/DaikoAI/status/1923167905052586030,Solana AI Tools,,,,,0,
+2,Treap,Hong Kong,0xWHU/ 武汉大学 Web3 俱乐部,neko-sol,"基于 Solana 区块链和 AI 技术的二次元猫娘养成游戏 MVP 版本
+
+核心功能
+✅ 钱包连接: 支持 Phantom 和 Solflare 钱包
+✅ Solana Devnet 集成: 完整的区块链交互
+✅ 好感度系统: 基于 SPL Token 的链上好感度存储
+✅ 实时余额查询: 查看钱包 SOL 余额
+✅ Devnet 空投: 获取测试 SOL
+✅ 好感度等级系统: 6 个等级从初识到至高羁绊
+链上操作
+创建好感度 Token Mint（每个猫娘独立）
+铸造好感度 Token 到用户账户
+实时查询好感度分数
+所有交易可在 Solana Explorer 查看","MVP Version of a 2D Catgirl Raising Game Based on Solana Blockchain and AI Technology
+
+Core Features
+✅ Wallet Connection: Supports Phantom and Solflare wallets
+✅ Solana Devnet Integration: Complete blockchain interaction
+✅ Affection System: On-chain affection storage based on SPL Tokens
+✅ Real-time Balance Inquiry: View your wallet's SPL balance
+✅ Devnet Airdrop: Obtain test SPL
+✅ Affection Level System: 6 levels from initial acquaintance to ultimate bond
+On-chain Operations
+Create Affection Token Mint (individual for each catgirl)
+Mint Affection Tokens to your user account
+Real-time Affection Score Inquiry
+All transactions can be viewed in Solana Explorer",https://github.com/TreapGoGo/neko-sol,,https://github.com/TreapGoGo/neko-sol,,"Swarms AI API, Solana AI Tools",,,,,0,
+3,Gladx,Hong Kong,0xWHU/ 武汉大学 Web3 俱乐部,sol-dream,"个创新的去中心化应用，使用AI将您的梦境片段补全成完整故事，并永久记录在Solana区块链上。
+
+✨ 特性
+🔗 Phantom钱包集成 - 安全便捷的钱包连接
+🤖 AI驱动 - 使用OpenAI GPT-4模型将梦境片段补全成完整故事
+⛓️ 区块链存储 - 将梦境永久记录在Solana区块链上
+🎨 现代化UI - 简洁美观的用户界面
+🚀 轻量级 - 纯前端实现，无需后端服务器","An innovative decentralized application that uses AI to complete your dream fragments into a full story and permanently record it on the Solana blockchain.
+
+✨ Features
+
+🔗 Phantom Wallet Integration - Secure and convenient wallet connection
+
+🤖 AI-Powered - Uses OpenAI GPT-4 model to complete dream fragments into a full story
+
+⛓️ Blockchain Storage - Permanently records dreams on the Solana blockchain
+
+🎨 Modern UI - Clean and beautiful user interface
+
+🚀 Lightweight - Pure front-end implementation, no back-end server required",https://github.com/TreapGoGo/sol-dream,,https://github.com/TreapGoGo/sol-dream,,"Solana AI Tools, Swarms AI API",,,,,0,
+4,Rafael Oliveira,Brazil,Other,AurumGrid,"Aurumgrid AUI – Artificial Universal Intelligence
+","Aurumgrid AUI – Artificial Universal Intelligence
+",https://github.com/Aurumgrid/aurumgrid-aui,https://github.com/Aurumgrid/aurumgrid-aui,https://github.com/Aurumgrid/aurumgrid-aui,https://x.com/RafaelO9416467/status/1978837487494516820,"Solana AI Tools, Aethir GPU Compute, Swarms AI API",,,,,0,
+5,Michael Afolabi,Nigeria,Superteam NG,Wojat,"Wojat is a comprehensive, AI-powered memecoin hunting platform that combines real-time data collection, social media analysis, and AI-driven insights to help traders discover the next big memecoin opportunities. Built with modern web technologies and powered by advanced AI agents.","Wojat is a comprehensive, AI-powered memecoin hunting platform that combines real-time data collection, social media analysis, and AI-driven insights to help traders discover the next big memecoin opportunities. Built with modern web technologies and powered by advanced AI agents.",https://drive.google.com/drive/folders/1-qESLXy-PvwB-L0CTYeUlxs-KpiUVATq?usp=sharing,https://drive.google.com/drive/folders/1-qESLXy-PvwB-L0CTYeUlxs-KpiUVATq?usp=sharing,https://github.com/Afoxcute/wojat,https://x.com/wojat118721/status/1979682642309341282,Solana AI Tools,,,,,0,
+6,Brooks Shui,Taiwan,Nankai University Blockchain Association / 南开大学区块链协会,SPR Platform,"🦹🏻‍♀️🔮SPR1.0: The ATH-Powered VLM estimation platform (🔗https://reflexresearches.com/)
+
+What We Built (and Why)
+
+SPR makes some difference. It's an autonomous platform that uses a swarm of our custom-built AI agents to handle the entire assessment process in minutes, not days. We let customers and businesses spare their time and improve the efficiency.
+
+The Problem We're Fixing
+
+We remove the personality in recycling, and spare the cost of the laboratory and long time. Also, thinking of the high training cost of a VLM-model, we use the Aethir GPU to shrink its fee.
+
+Our Solution
+
+The model consists of two versions: image recognition and video recognition. 
+
+The image recognition module can accurately capture detailed appearance features of smartphones, detecting physical damages such as screen scratches, frame dents, and back cover wear in milliseconds. Meanwhile, it quickly verifies core configuration information including processor model, RAM capacity, and storage size through hardware parameter recognition algorithms. 
+
+The video recognition module further breaks through the limitations of static recognition by analyzing dynamic footage of smartphone boot-up demonstrations and functional operations to determine if there are issues such as color cast, light leakage, or touch failure on the screen. It also accurately identifies whether the camera lens has scratches, bubbles, or cracks, and fully verifies the integrity of functions such as camera focusing and flash. This multi-dimensional intelligent detection method constructs a full-lifecycle evaluation system for smartphones, from hardware performance to appearance wear, providing objective and accurate data support for pricing.","🦹🏻‍♀️🔮SPR1.0: The ATH-Powered VLM estimation platform (🔗https://reflexresearches.com/)
+
+What We Built (and Why)
+
+SPR makes some difference. It's an autonomous platform that uses a swarm of our custom-built AI agents to handle the entire assessment process in minutes, not days. We let customers and businesses spare their time and improve the efficiency.
+
+The Problem We're Fixing
+
+We remove the personality in recycling, and spare the cost of the laboratory and long time. Also, thinking of the high training cost of a VLM-model, we use the Aethir GPU to shrink its fee.
+
+Our Solution
+
+The model consists of two versions: image recognition and video recognition.
+
+The image recognition module can accurately capture detailed appearance features of smartphones, detecting physical damages such as screen scratches, frame dents, and back cover wear in milliseconds. Meanwhile, it quickly verifies core configuration information including processor model, RAM capacity, and storage size through hardware parameter recognition algorithms.
+
+The video recognition module further breaks through the limitations of static recognition by analyzing dynamic footage of smartphone boot-up demonstrations and functional operations to determine if there are issues such as color cast, light leakage, or touch failure on the screen. It also accurately identifies whether the camera lens has scratches, bubbles, or cracks, and fully verifies the integrity of functions such as camera focusing and flash. This multi-dimensional intelligent detection method constructs a full-lifecycle evaluation system for smartphones, from hardware performance to appearance wear, providing objective and accurate data support for pricing.",https://reflexresearches.com/,https://youtu.be/oprRqLLlRIQ?si=WXtOnpnyM9HN0WDI,https://github.com/paterleng/second_recycling_system,https://x.com/zhangyuxia4454/status/1980183358253756779?s=46,Aethir GPU Compute,,,,,0,
+7,Ozan Andaç,Poland,DoraHacks,Elowen,"Elowen is a decentralized AI project that allows users to chat with fictional and nonfictional characters without censorship while contributing to the development of AI
+models.
+
+The platform is designed to be community-driven, enabling creators to earn $ELW
+tokens through periodic reward distribution based on the usage of their chatbots.
+
+$ELW is fully controlled by a Solana program, preventing any manual interference or
+large-scale token selloffs.
+
+As project-wise, you can think of it as a decentralized and censorless character.ai
+alternative.
+
+We have an ecosystem of tools:
+- Web App for builders & consumers
+- X (formerly Twitter) bot that impersonates a character and replies to threads (@elowenbot)
+- Telegram Bot to move chatting beyond the website
+- Public API
+- Solana Program & Token (Currently on Testnet)","Elowen is a decentralized AI project that allows users to chat with fictional and nonfictional characters without censorship while contributing to the development of AI
+models.
+
+The platform is designed to be community-driven, enabling creators to earn $ELW
+tokens through periodic reward distribution based on the usage of their chatbots.
+
+$ELW is fully controlled by a Solana program, preventing any manual interference or
+large-scale token selloffs.
+
+As project-wise, you can think of it as a decentralized and censorless character.ai
+alternative.
+
+We have an ecosystem of tools:
+- Web App for builders & consumers
+- X (formerly Twitter) bot that impersonates a character and replies to threads (@elowenbot)
+- Telegram Bot to move chatting beyond the website
+- Public API
+- Solana Program & Token (Currently on Testnet)",https://drive.google.com/file/d/1odChCG-RZeiH7i1OjR88dUitb2h1pkJY/view?usp=sharing,https://elowen.ai,https://github.com/elowen-ai,https://x.com/OzanAndac_/status/1981922432689619368,Solana AI Tools,,,,,0,
+8,Shivam Agarwal,India,Other,SolGame,"A lightweight pixel **multicharacter**, Play To Earn dungeon game built on the Solana Devnet Blockchain, built with Phaser, powered by Metaplex NFT Marketplace Protocol. Our motivation is to enable users to own what they earn.","A lightweight pixel **multicharacter**, Play To Earn dungeon game built on the Solana Devnet Blockchain, built with Phaser, powered by Metaplex NFT Marketplace Protocol. Our motivation is to enable users to own what they earn.",https://docs.google.com/presentation/d/1g4LZlb-SBxnCUIOofO7lvPPPeMLYq664hZqJFO08Zt4/edit?usp=sharing,https://sol-game-six.vercel.app/,https://github.com/ShivamAgarwal-code/SolGame.git,,"Solana AI Tools, Swarms AI API",,,,,0,
+9,Fawzan Pima,Ghana,SG Union,Sol Terminal," An mcp server for solana that allows ai agents to gain context of solana capabilities like  sending solana , checking sol balance , manage sol accounts and wallets getting sol address al without needing a sol app installed you just connect the mcp to your agent and strt using it , u add your private key in the mcp env . Ware giving ai agents the autonomous capabilities to run activities onchain."," An mcp server for solana that allows ai agents to gain context of solana capabilities like  sending solana , checking sol balance , manage sol accounts and wallets getting sol address al without needing a sol app installed you just connect the mcp to your agent and strt using it , u add your private key in the mcp env . Ware giving ai agents the autonomous capabilities to run activities onchain.",https://www.loom.com/share/3c1295e0f80149e792b7a6f65bb45c1e,https://fozagtx.github.io/SolanaAiTerminal/,https://github.com/fozagtx/SolanaAiTerminal,https://youtu.be/iSs1Lf8n-fw?si=B5nUkyld1RW7yjjF,Solana AI Tools,,,,,0,
+10,Riadh M belarbi,United Kingdom of Great Britain and Northern Ireland,Imperial Blockchain,toky.fun,"Toky.fun is an all in one platform ecosystem allowing users to launch projects and grow them with no code, using AI agents and leveraging swarms. aimed at Web3 founders, small teams and non technicals, with toky.fun you can vibe code websites, mobile apps, manage your socials, moderate your group chats and get help with compliance, and of course launch tokens where you need them! ","Toky.fun is an all in one platform ecosystem allowing users to launch projects and grow them with no code, using AI agents and leveraging swarms. aimed at Web3 founders, small teams and non technicals, with toky.fun you can vibe code websites, mobile apps, manage your socials, moderate your group chats and get help with compliance, and of course launch tokens where you need them! ",https://aisolana.s3.eu-north-1.amazonaws.com/toky.fun+presentation.MP4,https://aisolana.s3.eu-north-1.amazonaws.com/toky2.0.mp4,https://github.com/its-mc/toky.fun.git,,Solana AI Tools,,,,,0,
+11,Yadidya Medepalli,United Kingdom of Great Britain and Northern Ireland,Other,Nebula AI,"Nebula Protocol is the world's first decentralized Earth observation platform where autonomous AI agents with their own Solana wallets monitor our planet 24/7 and record findings immutably on-chain. Nine specialized AI agents (Forest Guardian, Ice Sentinel, Disaster Responder, etc.) independently sign blockchain transactions, execute environmental missions, and mint NFTs demonstrating autonomous AI-driven blockchain operations that address centralized data silos and enable verifiable disaster prevention. Fully deployed on Solana with smart contracts, voice commands, and mind- blowing visualization proving AI agents can autonomously operate blockchain infrastructure at scale.
+
+Demo link at: https://x.com/MYadidya/status/1983074064211308648
+or
+Youtube link: https://youtu.be/fJrnTWOWPRM","Nebula Protocol is the world's first decentralized Earth observation platform where autonomous AI agents with their own Solana wallets monitor our planet 24/7 and record findings immutably on-chain. Nine specialized AI agents (Forest Guardian, Ice Sentinel, Disaster Responder, etc.) independently sign blockchain transactions, execute environmental missions, and mint NFTs demonstrating autonomous AI-driven blockchain operations that address centralized data silos and enable verifiable disaster prevention. Fully deployed on Solana with smart contracts, voice commands, and mind- blowing visualization proving AI agents can autonomously operate blockchain infrastructure at scale.
+
+Demo link at: https://x.com/MYadidya/status/1983074064211308648
+or
+Youtube link: https://youtu.be/fJrnTWOWPRM",https://nebv2article.netlify.app/,https://nebulav2.netlify.app/,https://github.com/YadidyaM/Nebula-2.0---Decentralized-Earth-Observation-Platform,https://x.com/MYadidya/status/1983074064211308648,"Solana AI Tools, Swarms AI API",,,,,0,
+12,Togo,Japan,N/A,TinyPay,"TinyPay is a crypto-native payment application built on Solana, enabling seamless real-world transactions with digital assets — even without an internet connection.
+We’re building the bridge between digital assets and everyday spending, making crypto payments as effortless as cash or cards.","TinyPay is a crypto-native payment application built on Solana, enabling seamless real-world transactions with digital assets — even without an internet connection.
+We’re building the bridge between digital assets and everyday spending, making crypto payments as effortless as cash or cards.",https://docs.google.com/presentation/d/1kXA47K0ovv51GvYYEm2yWVHrwJYQLrtKMqMoS5wUhMk/edit?usp=sharing,https://www.youtube.com/watch?v=E59_zBE-Mao,https://github.com/TrustPipe/TinyPayContract-Solana,https://x.com/TrustLucian/status/1981912066761056372,Solana AI Tools,,,,,0,
+13,Alan Wang,Japan,solar,foxhole.ai,"Foxhole AI monitors influential Twitter accounts for crypto keywords and instantly delivers verified contract addresses to users for trading. 
+
+","Foxhole AI monitors influential Twitter accounts for crypto keywords and instantly delivers verified contract addresses to users for trading. 
+
+",https://youtu.be/nn3zgyBGgdQ?si=xYHt87szURiqvVZz,https://youtu.be/nn3zgyBGgdQ?si=xYHt87szURiqvVZz,https://github.com/foxholeAI/foxholeAI,https://x.com/alan_ywang/status/1984315036429664509,"Solana AI Tools, Aethir GPU Compute, Swarms AI API",,,,,0,

examples/guides/hackathons/README.md

@@ -0,0 +1,18 @@
+# Hackathon Examples
+
+This directory contains hackathon project examples and implementations.
+
+## Subdirectories
+
+### Hackathon September 27
+- [hackathon_sep_27/](hackathon_sep_27/) - September 27 hackathon projects
+  - [api_client.py](hackathon_sep_27/api_client.py) - API client implementation
+  - [diet_coach_agent.py](hackathon_sep_27/diet_coach_agent.py) - Diet coach agent
+  - [nutritional_content_analysis_swarm.py](hackathon_sep_27/nutritional_content_analysis_swarm.py) - Nutritional analysis swarm
+  - [nutritonal_content_analysis_swarm.sh](hackathon_sep_27/nutritonal_content_analysis_swarm.sh) - Analysis script
+  - [pizza.jpg](hackathon_sep_27/pizza.jpg) - Sample image
+
+## Overview
+
+This directory contains real hackathon projects built with Swarms, demonstrating practical applications and creative uses of the framework. These examples showcase how Swarms can be used to build domain-specific solutions quickly.
+

examples/guides/nano_banana_jarvis_agent/README.md

@@ -0,0 +1,18 @@
+# Nano Banana Jarvis Agent
+
+This directory contains the Nano Banana Jarvis agent example, demonstrating vision and multimodal capabilities.
+
+## Examples
+
+- [jarvis_agent.py](jarvis_agent.py) - Main Jarvis agent implementation
+- [img_gen_nano_banana.py](img_gen_nano_banana.py) - Image generation example
+
+## Images
+
+- Sample images included: building.jpg, hk.jpg, image.jpg, miami.jpg
+- [annotated_images/](annotated_images/) - Directory containing annotated image examples
+
+## Overview
+
+The Nano Banana Jarvis agent demonstrates advanced vision and multimodal capabilities, including image analysis, image generation, and visual understanding. This example showcases how to build agents that can process and generate visual content.
+

examples/guides/web_scraper_agents/README.md

@@ -0,0 +1,13 @@
+# Web Scraper Agents
+
+This directory contains examples demonstrating web scraping capabilities with agents.
+
+## Examples
+
+- [batched_scraper_agent.py](batched_scraper_agent.py) - Batched web scraping agent
+- [web_scraper_agent.py](web_scraper_agent.py) - Basic web scraper agent
+
+## Overview
+
+These examples demonstrate how to build agents capable of web scraping, extracting information from websites, and processing web content. The batched version shows how to handle multiple URLs efficiently, while the basic example demonstrates core scraping functionality.
+

examples/mcp/agent_examples/README.md

@@ -0,0 +1,15 @@
+# MCP Agent Examples
+
+This directory contains examples demonstrating agent implementations using Model Context Protocol (MCP).
+
+## Examples
+
+- [agent_mcp_old.py](agent_mcp_old.py) - Legacy MCP agent implementation
+- [agent_multi_mcp_connections.py](agent_multi_mcp_connections.py) - Multi-MCP connection agent
+- [agent_tools_dict_example.py](agent_tools_dict_example.py) - Agent tools dictionary example
+- [mcp_exampler.py](mcp_exampler.py) - MCP example implementation
+
+## Overview
+
+MCP agent examples demonstrate how to build agents that leverage the Model Context Protocol for enhanced context management and tool integration. These examples show various patterns for connecting agents to MCP servers and using MCP tools.
+

examples/mcp/mcp_utils/README.md

@@ -0,0 +1,27 @@
+# MCP Utils
+
+This directory contains utility functions and helpers for MCP implementations.
+
+## Examples
+
+- [client.py](client.py) - MCP client implementation
+- [mcp_client_call.py](mcp_client_call.py) - MCP client call utilities
+- [mcp_multiple_servers_example.py](mcp_multiple_servers_example.py) - Multiple MCP servers example
+- [mcp_multiple_tool_test.py](mcp_multiple_tool_test.py) - Multiple tool testing
+- [multiagent_client.py](multiagent_client.py) - Multi-agent MCP client
+- [singleagent_client.py](singleagent_client.py) - Single agent MCP client
+- [test_multiple_mcp_servers.py](test_multiple_mcp_servers.py) - Multiple server testing
+- [utils.py](utils.py) - General MCP utilities
+
+## Subdirectories
+
+- [utils/](utils/) - Additional utility functions
+  - [find_tools_on_mcp.py](utils/find_tools_on_mcp.py) - Tool discovery
+  - [mcp_execute_example.py](utils/mcp_execute_example.py) - MCP execution example
+  - [mcp_load_tools_example.py](utils/mcp_load_tools_example.py) - Tool loading example
+  - [mcp_multiserver_tool_fetch.py](utils/mcp_multiserver_tool_fetch.py) - Multi-server tool fetching
+
+## Overview
+
+MCP utils provide helper functions, client implementations, and testing utilities for working with Model Context Protocol. These examples demonstrate how to connect to MCP servers, discover tools, execute operations, and manage multiple MCP connections.
+

examples/mcp/multi_mcp_guide/README.md

@@ -0,0 +1,14 @@
+# Multi-MCP Guide Examples
+
+This directory contains examples demonstrating multi-MCP connection patterns and guides.
+
+## Examples
+
+- [agent_mcp.py](agent_mcp.py) - Agent MCP implementation
+- [mcp_agent_tool.py](mcp_agent_tool.py) - MCP agent tool example
+- [okx_crypto_server.py](okx_crypto_server.py) - OKX crypto MCP server example
+
+## Overview
+
+Multi-MCP guide examples demonstrate how to connect agents to multiple MCP servers simultaneously, manage multiple tool sets, and coordinate operations across different MCP connections. These examples provide guidance for building complex MCP-based agent systems.
+

examples/mcp/servers/README.md

@@ -0,0 +1,15 @@
+# MCP Server Examples
+
+This directory contains examples demonstrating MCP server implementations.
+
+## Examples
+
+- [mcp_agent_tool.py](mcp_agent_tool.py) - MCP agent tool server
+- [mcp_test.py](mcp_test.py) - MCP server testing
+- [okx_crypto_server.py](okx_crypto_server.py) - OKX crypto MCP server
+- [test.py](test.py) - Server testing
+
+## Overview
+
+MCP server examples demonstrate how to implement Model Context Protocol servers that expose tools and capabilities to agents. These examples show server setup, tool registration, request handling, and domain-specific server implementations.
+

examples/multi_agent/agent_rearrange_examples/README.md

@@ -0,0 +1,12 @@
+# Agent Rearrangement Examples
+
+This directory contains examples demonstrating agent rearrangement functionality in multi-agent systems.
+
+## Examples
+
+- [rearrange_test.py](rearrange_test.py) - Test agent rearrangement functionality
+
+## Overview
+
+Agent rearrangement allows dynamic reconfiguration of agent teams and workflows during execution, enabling adaptive multi-agent systems that can reorganize based on task requirements or performance metrics.
+

examples/multi_agent/agent_router_examples/README.md

@@ -0,0 +1,12 @@
+# Agent Router Examples
+
+This directory contains examples demonstrating agent routing functionality for directing tasks to appropriate agents.
+
+## Examples
+
+- [agent_router_example.py](agent_router_example.py) - Agent routing implementation example
+
+## Overview
+
+Agent routing enables intelligent task distribution across multiple agents based on capabilities, availability, or task characteristics. This allows for efficient load balancing and optimal agent selection.
+

examples/multi_agent/asb/README.md

@@ -0,0 +1,17 @@
+# Auto Swarm Builder (ASB) Examples
+
+This directory contains examples demonstrating the Auto Swarm Builder, which automatically creates and configures agent swarms.
+
+## Examples
+
+- [asb_research.py](asb_research.py) - Research-focused ASB implementation
+- [auto_agent.py](auto_agent.py) - Automated agent creation
+- [auto_swarm_builder_example.py](auto_swarm_builder_example.py) - Complete ASB example
+- [auto_swarm_builder_test.py](auto_swarm_builder_test.py) - ASB testing suite
+- [auto_swarm_router.py](auto_swarm_router.py) - Router for auto-generated swarms
+- [content_creation_asb.py](content_creation_asb.py) - Content creation with ASB
+
+## Overview
+
+The Auto Swarm Builder (ASB) automatically generates and configures multi-agent swarms based on task requirements, reducing manual setup overhead and enabling rapid prototyping of agent systems.
+

examples/multi_agent/board_of_directors/README.md

@@ -0,0 +1,14 @@
+# Board of Directors Examples
+
+This directory contains examples demonstrating board of directors patterns for multi-agent decision-making.
+
+## Examples
+
+- [board_of_directors_example.py](board_of_directors_example.py) - Full board simulation
+- [minimal_board_example.py](minimal_board_example.py) - Minimal board setup
+- [simple_board_example.py](simple_board_example.py) - Simple board example
+
+## Overview
+
+Board of directors patterns simulate corporate governance structures where multiple agents collaborate to make decisions, vote on proposals, and manage organizational tasks. This pattern is useful for complex decision-making scenarios requiring multiple perspectives.
+

examples/multi_agent/caching_examples/README.md

@@ -0,0 +1,14 @@
+# Caching Examples
+
+This directory contains examples demonstrating caching strategies for multi-agent systems.
+
+## Examples
+
+- [example_multi_agent_caching.py](example_multi_agent_caching.py) - Multi-agent caching implementation
+- [quick_start_agent_caching.py](quick_start_agent_caching.py) - Quick start guide for caching
+- [test_simple_agent_caching.py](test_simple_agent_caching.py) - Simple caching tests
+
+## Overview
+
+Caching in multi-agent systems improves performance by storing frequently accessed data and computation results. These examples demonstrate various caching strategies for agent interactions, tool calls, and shared state.
+

examples/multi_agent/concurrent_examples/README.md

@@ -0,0 +1,22 @@
+# Concurrent Examples
+
+This directory contains examples demonstrating concurrent execution patterns for multi-agent systems.
+
+## Examples
+
+- [asi.py](asi.py) - ASI (Artificial Super Intelligence) example
+- [concurrent_example_dashboard.py](concurrent_example_dashboard.py) - Dashboard for concurrent workflows
+- [concurrent_example.py](concurrent_example.py) - Basic concurrent execution
+- [concurrent_mix.py](concurrent_mix.py) - Mixed concurrent patterns
+- [concurrent_swarm_example.py](concurrent_swarm_example.py) - Concurrent swarm execution
+- [streaming_concurrent_workflow.py](streaming_concurrent_workflow.py) - Streaming with concurrency
+
+## Subdirectories
+
+- [streaming_callback/](streaming_callback/) - Streaming callback examples
+- [uvloop/](uvloop/) - UVLoop integration examples for high-performance async execution
+
+## Overview
+
+Concurrent execution enables multiple agents to work simultaneously, significantly improving throughput and reducing latency. These examples demonstrate various concurrency patterns including parallel processing, async workflows, and streaming responses.
+

examples/multi_agent/council/README.md

@@ -0,0 +1,14 @@
+# Council Examples
+
+This directory contains examples demonstrating council patterns for multi-agent evaluation and decision-making.
+
+## Examples
+
+- [council_judge_evaluation.py](council_judge_evaluation.py) - Judge evaluation system
+- [council_judge_example.py](council_judge_example.py) - Basic council example
+- [council_of_judges_eval.py](council_of_judges_eval.py) - Evaluation framework
+
+## Overview
+
+Council patterns involve multiple agents acting as judges or evaluators, providing diverse perspectives and assessments. This is useful for quality control, peer review, and consensus-building scenarios.
+

examples/multi_agent/council_of_judges/README.md

@@ -0,0 +1,14 @@
+# Council of Judges Examples
+
+This directory contains examples demonstrating council of judges patterns for multi-agent evaluation systems.
+
+## Examples
+
+- [council_judge_complex_example.py](council_judge_complex_example.py) - Complex council setup
+- [council_judge_custom_example.py](council_judge_custom_example.py) - Custom council configuration
+- [council_judge_example.py](council_judge_example.py) - Basic council of judges example
+
+## Overview
+
+Council of judges patterns extend the basic council pattern with more sophisticated evaluation mechanisms, custom scoring systems, and complex decision-making workflows. These examples demonstrate advanced judge coordination and evaluation strategies.
+

examples/multi_agent/debate_examples/README.md

@@ -0,0 +1,12 @@
+# Debate Examples
+
+This directory contains examples demonstrating debate patterns for multi-agent systems.
+
+## Overview
+
+Debate patterns enable agents to engage in structured discussions, present arguments, and reach conclusions through discourse. This pattern is useful for exploring multiple perspectives on complex topics and arriving at well-reasoned decisions.
+
+## Note
+
+This directory is currently being populated with debate examples. Check back soon for implementations!
+